Circuit Discovery

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 29

Oct 1, 2026cs.LG

Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability

Mechanistic interpretability aims to recover the internal computations responsible for model behavior. Progress in automated circuit discovery is often framed as a search problem: better attribution or optimization should identify better mechanisms. This assumes that the evaluation objective can recognize a better circuit once it is found. We show that intervention-defined faithfulness can instead prefer an equally sized circuit that reproduces the model's behavior less well, creating an objective-level recovery gap. Across four human-reference tasks and InterpBench, we compare validation faithfulness with behavior on held-out prompts under fixed ordinary resampling. The behavioral criterion is agreement with the intact model, including its mistakes, except on Greater-Than, where we use semantic accuracy. Controlled reference edits reveal misranking without any discovery algorithm, and outputs of EAP, EAP-IG, ACDC, and Edge-SP exhibit the same failure. Under resampling, KL misranks 9.4%-41.2% of candidate pairs across these methods on the human-reference tasks. We investigate context distortion as an explanation: replacing excluded signals changes the inputs on which retained components operate. Restoring selected signals from the recipient's intact-model execution repairs 96 of 100 persistent KL misrankings from the discovery pool on both validation and held-out prompts. The circuits and their original behavioral scores remain unchanged. These findings show why better discovery alone is insufficient when its objective rewards the wrong candidate.

Chuqin Geng, Li Zhang, Haolin Ye +3

University of Toronto · McGill University

Circuit Discovery Mechanistic Interpretability Explainability Evaluation

Sep 21, 2026cs.AI

Attention as a Routing Graph: Live Circuit Extraction from a Single Forward Pass

Finding circuits in language models usually means running many careful interventions. We try something simpler: treat attention as a routing map from one forward pass, keep a small set of routes that point toward the answer, and ask whether those routes actually matter. They often do. On induction and IOI (tasks where the "right" circuit is already known), ablating our extracted edges hurts the model much more than ablating a random set of the same size. We evaluate n=100 prompts per cell on GPT-2 Small, GPT-2 Medium, and Pythia-410M, with paired gap tests and bootstrap confidence intervals. The extract step costs one forward; a head-by-head patch sweep costs about two orders of magnitude more. We are not claiming a complete circuit atlas. We are claiming a cheap sketch that carries real causal signal on known tasks, with clear failure modes when it does not. Code and evaluation artifacts are at https://github.com/Aquinf03/live-circuit-routing.

Ash Manvi, Samreena Tajreen

Aquin Labs

Circuit Discovery Attention Mechanisms Circuits in Language Models Causal Interventions in Language Models

Sep 20, 2026cs.LG

Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs

Mechanistic interpretability defines features as the fundamental units of a neural network and circuits as the weighted subgraphs that carry out its computation. Because individual neurons are polysemantic, Cross-Layer Transcoders (CLTs) were introduced as a way to approximate a model's circuits by generating an attribution graph. The nodes of that graph, however, are unlabeled features: reading a graph means pruning it and then working out by hand what each surviving node means. To make CLTs easier to use for circuit discovery, we introduce Circuit-Diff, which intervenes on the model itself with a low-rank factual edit and takes the features whose role in the attribution graph changes under that edit as related to the edited knowledge. On the edits we examine, the flagged nodes are not only detectors of the object token: read off the CLT's released feature dashboards, they include features for the history, geography and associations surrounding the old and new objects. We formalize the method, measure how reliable a frozen CLT remains after a factual edit, test the selected nodes causally by patching them on up to 24 CounterFact edits, give a case study, and release an open-source implementation built on the circuit-tracer package, together with two further tools (multi-prompt aggregation and rule-based supernode labeling).

Edward G. Friedman, Xiangchen Song

School of Computer Science Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213

Circuit Discovery Mechanistic Interpretability Causal Interventions in Language Models

Sep 11, 2026cs.SD

Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models

Transformer-based foundation models are powerful but opaque, motivating Mechanistic Interpretation methods to uncover the black-box by identifying small computation subgraphs responsible for a task. DiscoGP is a joint weight-and-edge circuit discovery framework originally developed for text decoders. We extend DiscoGP to speech encoders and present, to our knowledge, the first circuit discovery study for modern speech foundation models. Across HuBERT and Wav2Vec 2.0 on several speech classification tasks, we find that the discovered circuits are extremely compact, yet often match or even exceed the performance of the full pretrained encoder with the same downstream head. Through ablations, we show that these circuits reflect pretrained computation rather than random structure or task-head artifacts. We also introduce a memory-efficient DiscoGP variant that reduces the GPU memory cost of edge-circuit discovery at runtime from quartic to cubic. Overall, our results broaden Mechanistic Interpretation beyond text decoders and show that circuit-level analysis can reveal both explanatory structure and unexpected functional behavior in speech encoders.

Jiankun Wei, Ewan Dunbar, Gerald Penn

Department of Computer Science University of Toronto Toronto, Canada

Transformer Interpretability Circuit Discovery Speech Foundation Models

Sep 1, 2026cs.AI

Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems

Sharing analog integrated circuit designs remains difficult: foundry non-disclosure agreements restrict the process details a design depends on, and the testbenches behind published results are rarely released. We present analog-db, an open-source, versioned database built on a shareable design representation. A domain-specific language captures each design as a process-neutral topology, reusable testbenches, and a machine-readable datasheet under one schema, so a design is shared in full and re-simulates on the process kits it is bound to. A parameterization scheme exposes functional sub-blocks and device sizes as named parameters that carry their matching constraints, making circuits composable and retargetable; a schema-governed contract and queryable catalog let AI design agents discover and reuse them directly. Across the regulator corpus, all 23 circuit-kit bindings on three open kits meet their own recorded specification bands (typical corner, matched devices, no layout) and 10 of 23 meet a common class band. Seventeen of the 23 imported sizings failed their testbenches and closed under a gm/ID sizing loop driven by the annotated sub-block roles, typically within one to three iterations. In a supervised case study, a coding agent working from the released artifacts sized the op-amp cores of a chopper instrumentation amplifier on an open 130nm kit, locating four hand-entry defects and a missing common-mode feedback loop that the sizing-only baseline did not repair. The database holds 68 circuits across sixteen classes, verifiable at schematic level under a tiered harness and tracked on a power/performance scoreboard, released at https://github.com/MacAnalog/spicexplorer-release.

Danial Noori Zadeh, Mohamed B. Elamien

The authors are with the Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada

Circuit Discovery Electronic Design Automation

Jul 23, 2026cs.CL

What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations

Do independently trained language models come to represent the same thing in the same way? We answer for code, extending a recently introduced concept-circuit extraction method to a 2x2 design -- Python and Rust crossed with Qwen2.5-Coder-7B and DeepSeek-Coder-V1-6.7B -- and measuring a complete inventory of grammatical concepts (58 Python, 57 Rust) identically in all four cells: the smallest design that separates what depends on the task, the language, and the model. The answer splits into three parts. What earns dedicated circuitry is set by the task: the models agree on which concepts receive circuits (Spearman

ρ

= 0.638 for Python, 0.673 for Rust, both p <

10^{-7}

). Where those circuits sit is set by the model: Qwen processes concepts in a late band (~L17-19), DeepSeek at L6-7, for both languages. How circuits grow across layers is also set by the model: Qwen gives its atomic concepts an early spike that DeepSeek does not. "Are circuits universal?" thus has no single answer: yes for What, no for Where and How -- universality is a property of representational content, not of computational organisation. None of this structure was fixed in advance. The agreement could have landed anywhere between independence and identity; it lands at

ρ\approx 0.65

. Rust constructs receive 2-3x more concept-specific circuitry than their Python equivalents, in both models. Both models share neurons between the languages (6/7 and 7/7 paired constructs), DeepSeek 1.94x more than Qwen -- a direction no prior result predicts. And Qwen binds nine keywords of Rust's type-and-trait machinery into one tight neuron cluster (Jaccard 0.535 vs null 0.112, p < 0.001), a semantic dimension invisible in surface syntax. Ablation and linear probes confirm the circuits are functional. All claims are scoped to this 2x2; whether the per-model profile predicts a third model is the designed next test.

Piotr Wilam

University College London

Circuit Discovery Language Model Introspection Circuits in Language Models Representation Geometry in Language Models Code Language Models

Jul 21, 2026cs.LG

CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability

Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implementations for discovery, evaluation, and intervention, as well as hand-authoring the contrastive prompts required by many discovery methods. This fragmentation makes methods difficult to compare and limits their application beyond canonical tasks. We introduce CircuitKIT, a source-available library that connects the circuit-analysis workflow through a typed, serializable representation. CircuitKIT provides a suite of discovery algorithms, declarative interfaces for mapping structured data into discovery tasks, complementary circuit diagnostics, and downstream application modules. Together, these components provide common infrastructure for conducting and comparing circuit analyses. The library, examples, notebooks, and documentation are released at https://github.com/Lexsi-Labs/CircuitKIT .

Pratinav Seth, Hem Gosalia, Aditya Kasliwal +1

Lexsi Labs

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Explainability Evaluation

Jul 21, 2026cs.LG

Circuit Claims Depend on What Is Extracted and How It Is Compared

Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior. We argue that this reading is under-determined: preserving behavior does not single out one circuit, because the claim it supports depends on which circuit is reported and how two circuits are compared. We make this concrete in a synthetic Lean tactic-prediction benchmark -- predicting the next step of a proof -- where fixed proof rules with randomized surface form let differences between extracted circuits be attributed to these choices rather than to the task. Across dense and weight-sparse checkpoints (most weights constrained to zero) of the same transformer, evaluated on atomic (single-rule) and compositional (multi-rule) proofs, we vary which extracted object is reported (a compact prediction-preserving circuit, a broader graph that also keeps surrounding read, write, and routing structure, or the smallest subgraph meeting a post-ablation loss threshold), and whether each attention head's query and key are represented jointly or separately. Exact component-to-component edge overlap is low and sensitive to these choices, at times dropping to a random baseline, while two coarser summaries stay stable: the set of selected attention heads, and the circuit-size ranking of conditions that differ in which supervised checkpoint initializes reinforcement learning (RL). The largest accuracy gains from RL on compositional proofs come with the most structure beyond the atomic circuits. A circuit-level claim is therefore well defined only once one states which circuit is reported, the pruning threshold used to extract it, and the level at which circuits are compared. We distill these requirements into a reporting practice for circuit-extraction studies.

Yang Sheng, Jie Fu

1Fudan University · 2Shanghai Innovation Institute · 3IQuest Research

Transformer Interpretability Circuit Discovery Circuits in Language Models

Jul 14, 2026cs.CL

A Shared Subcircuit Lets LLMs Count Down Across Tasks

Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table. These are all tasks that language models can do that requires tracking how many tokens remain before a target. In this work, we identify in Llama-3.1-70B-Instruct a general mechanism for performing these tasks: a "countdown subcircuit" that compares the current position to a goal length and estimates the time remaining until then. We first isolate a countdown subcircuit in a controlled setting, in which the model is tasked with writing a fixed-length sentence ending in a specified word. We then investigate the geometry of the representations used by the subcircuit, and find that the subcircuit uses an identical motif previously identified in a frontier LLM on a separate task, thus suggesting that this motif is shared across models. Finally, we use unsupervised probing on a natural language dataset to find a variety of other tasks where this subcircuit is used, including tasks where the goal length is inferred from context rather than explicitly stated. Our work suggests that reverse-engineering subcircuits allows us to understand how behaviors generalize from a single example to many different tasks and even models.

Jacob Dunefsky, Wes Gurnee, Emmanuel Ameisen

Yale University · Anthropic

Circuit Discovery Circuits in Language Models

Jul 2, 2026cs.LG

Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

Mechanistic interpretability seeks to explain transformer behavior through circuits: sets of internal components that causally support a behavior. However, self-repair creates a blind spot: ablating a primary component can activate a dormant backup, so a circuit that explains behavior in the intact model can become incomplete under the intervention used to test it. We formulate this gap as conditional circuit completion: given a primary set, identify components that become causally important after its removal. We introduce conditional co-ablation (CoAx), which ranks candidates by growth in ablation effect after primary-set removal. We show that a perfectly dormant backup can be indistinguishable from an irrelevant component to per-unit intact-state scores, whereas its conditional effect change exactly aggregates all interaction orders linking it to the removed set. On GPT-2-small's Indirect Object Identification (IOI) circuit, CoAx recovers the documented backup heads at 0.941 ROC-AUC, versus 0.815 for the strongest intact-state attribution baseline and 0.758 for the matched conditional-energy control. Recovery drops to 0.40 +/- 0.13 AUC for alternative component sets matched in behavioral effect, output displacement, and depth, showing that recovery is specific to the removed circuit. Beyond recovery, the CoAx-selected heads are causally load-bearing: freezing them after primary removal sharply reduces the IOI margin, while adding them to the incomplete circuit reduces incompleteness from 0.75 to 0.21. More broadly, conditional growth aligns with intervention-derived repair in 11/12 held-out instances across 4 mechanism clusters, and CoAx completions outperform matched random completions on all 8 non-GPT-2 models spanning 6 architecture families. Together, causal explanations of self-repairing transformers must account for backup circuitry when primary components fail.

Zhiren Gong, He Lu, Tiantong Wang +6

College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Causal Interventions in Language Models

Jun 24, 2026cs.LG

FactorLibrary: From Polynomials to Circuits via Recursive Subgoals

Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We formulate it as a reinforcement learning problem in two directions, bottom-up and top-down. To address the challenge of a fast-growing combinatorial search space, we introduce FactorLibrary, which stores factorizable subexpressions that serve as reusable subgoals across training episodes. We trained a bottom-up agent with Gumbel-PPO-MCTS and two top-down agents with PPO+MCTS and SAC. The PPO+MCTS top-down agent exhibited the most stable performance, finding certified optimal circuits up to complexity

8

with a success rate of

91.8\%

.

Rohan Pandey, Michael Ruofan Zeng, Weikun K. Zhang +5

University of Washington, Seattle, WA, USA.

Circuit Discovery Reinforcement Learning RL for Combinatorial Optimization

Jun 19, 2026cs.LG

Targeted Recovery of Weight-Space Mechanisms From Neural Networks

Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations. However, scaling PD to large models requires vast compute, making it a costly and risky endeavor. Here we propose targeted PD (tPD), which identifies only the components that process specific inputs of interest -- from isolated prompts to large subtasks -- by introducing a high-rank catch-all component that handles all non-target data. We validate tPD on toy models and on transformer language models trained on The Pile, where it recovers reproducible, mechanistically faithful circuits. We extract a CSS-only submodel of a 4-block transformer using 7% of the FLOPs of its published decomposition, and in a 12-block transformer we surgically ablate and rewire memorized sequences, with negligible side effects on other inputs.

Antoine Vigouroux, Lee Sharkey

1MATS · 2Goodfire

Transformer Interpretability Circuit Discovery Mechanistic Interpretability Neural Network Interpretability

Jun 15, 2026cs.LG

Scalable Circuit Learning for Interpreting Large Language Models

A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circuits hard to interpret. Sparse autoencoder (SAE) features alleviate this, but their high dimensionality makes existing intervention-based circuit learning methods computationally prohibitive. We propose CircuitLasso, a scalable circuit-learning approach based on sparse linear regression. CircuitLasso recovers circuits whose structural accuracy matches that of state-of-the-art intervention-based methods on the benchmark data, at a fraction of the computational cost. For interpretability, CircuitLasso efficiently uncovers relationships among SAE features, showing how human-interpretable semantic features propagate through the model and influence its predictions. Finally, we validate the utility of our learned circuits by leveraging their insights to achieve comparable performance at substantially lower cost on a domain-generalization task.

Naiyu Yin, Dennis Wei, Tian Gao +3

Lehigh University, Mathematics Department, Bethlehem, USA · IBM Research, Yorktown Heights, USA.

Circuit Discovery LLM Interpretability Mechanistic Interpretability Circuits in Language Models

Jun 15, 2026cs.LG

Demystifying Variance in Circuit Discovery of LLMs

Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model components that are crucial for performing a given task. Although the current state-of-the-art method (EAP-IG) performs well on the metric of (un)faithfulness, it suffers from substantial variability. This includes resampling variance, where the circuit changes when we probe with a new batch of data from the same distribution; rephrasing variance, where the discovered circuit shifts when the prompts are rephrased; and sample-wise variance, where a circuit with low population unfaithfulness exhibits large fluctuations in unfaithfulness across individual samples. This paper studies the roots of these variances. We demonstrate that CEAP, our new circuit discovery method that improves upon EAP-IG with a theoretical guarantee, can substantially lessen resampling variance. We further show that rephrasing variance arises because prompts with different templates tend to activate different circuits in the model. This leads us to argue that it may be challenging to find a comprehensive circuit that explains and controls the model's behavior on a task, which can be expressed in countless templates, suggesting that LLMs may be inherently hard to steer. We show that sparsity, which has been claimed to form more compact and interpretable task circuits, fails to solve this problem. Regarding sample-wise variance, we argue that it is largely benign: extremely poor unfaithfulness scores often stem from how unfaithfulness is defined, rather than from defects in the measured circuits. We show that the magnitude of unfaithfulness is affected by selective contribution scaling, a neural mechanism that accounts for the extremely poor scores sometimes observed.

Frank Zhengqing Wu, Francesco Tonin, Volkan Cevher

Laboratory for Information and Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Laboratory for Informationand Inference Systems (LIONS) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland

Prompt Sensitivity Circuit Discovery LLM Interpretability Mechanistic Interpretability Explanation Stability Circuits in Language Models

Jun 14, 2026cs.LG

Circuit Tracing in Autoregressive Protein Language Models

Protein language models (pLMs) can generate novel protein sequences with properties beyond those observed in nature, yet the mechanisms underlying protein generation remain poorly understood. Existing mechanistic interpretability methods based on sparse autoencoders and transcoders primarily focus on protein representation learning models and do not capture the computation required for autoregressive generation. Here, we introduce ProGenMech, a mechanistic interpretability framework for generative protein language models that extends cross-layer transcoders (CLTs) to ProGen3, a sparse Mixture-of-Experts model trained for both causal generation and span infilling. Unlike per-layer approaches, CLTs reconstruct each layer using sparse latent variables from all preceding layers, enabling faithful recovery of inter-layer generative computation. We further develop a zero-shot circuit discovery framework to identify sparse latent circuits responsible for protein generation and fitness prediction. In causal generation and zero-shot fitness estimation tasks, ProGenMech outperforms local transcoder baselines in recovering ProGen3's probability distribution and functional scoring behavior, while matching the original model's generative distribution in span infilling tasks. Moreover, the recovered circuits reveal biologically meaningful motifs and functional regions associated with conserved sequence patterns and protein fitness landscapes, establishing a foundation for interpretable and steerable protein generation.

Darin Tsui, William Deinzer, Daniel Saeedi +1

School of Electrical and Computer Engineering, Georgia Institute of Technology, Atltanta, GA.

Circuit Discovery Protein Fitness Prediction Protein Language Models Autoregressive Language Modeling Mechanistic Interpretability Molecular Generation

Jun 8, 2026cs.LG

Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes

Interpretability increasingly treats groups of components, not individual units, as the basic object, and proposes to find them by clustering co-activation statistics. We ask whether such a cheap signal actually identifies an attention-head circuit. Adapting a sparse-autoencoder clustering recipe to attention heads -- but validating by causal ablation rather than reconstruction -- we cluster heads and then run a closure test: ablate the discovered community and compare per-example damage to matched-random controls. Across two dense 1B-scale models (Pythia 1B, OLMo 1B) and two input distributions, the communities pass closure. In a Mixture-of-Experts model (OLMoE-1B-7B), route-conditional clustering recovers a statistically real signal that nonetheless does not survive closure -- ablation improves loss, the wrong direction. Extending closure across training, attention-target selectivity and participation ratio decouple from function in both directions. We conclude that a cheap signal is a circuit proposal, not a confirmed circuit; closure is what separates them.

Yongzhong Xu

Transformer Interpretability Circuit Discovery Attention Head Analysis Clustering Multi-Head Attention

Jun 4, 2026cs.CL

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery

Circuit discovery methods identify subgraphs that explain specific model behaviors, and structural differences between discovered circuits are commonly interpreted as evidence of distinct mechanisms. We test this assumption by varying input statistics while holding the task fixed, and show that the resulting structural differences exhibit apparent specialization but do not correspond to functional differences, a pattern we term phantom specialization. Using Literal Sequence Copying across four token-frequency bands plus a control condition in five Pythia models (70M-1.4B), we extract 75 circuits and find that structurally distinct circuits implement the same computation: band-specific edges transfer broadly across bands, a core shared across most bands recovers at least 99% of circuit performance, and causal interchange interventions confirm that internal representations are interchangeable across frequency bands. Repeated extractions within the same frequency band further suggest that discovery algorithms sample from an equivalence class of valid subgraphs rather than recovering a unique mechanism. Standard evaluation practice obscures this pattern: source-level evaluation inflates apparent faithfulness, while edge-level evaluation reveals the many-to-one mapping from structure to function. Our results show that structural differences between circuits are not sufficient evidence for distinct mechanisms, and that exposing this requires edge-level evaluation and cross-condition transfer tests.

Alireza Bayat Makou, Jingcheng Niu, Subhabrata Dutta +1

UKP Lab, Technical University of Darmstadt · National Research Center for Applied Cybersecurity ATHENE

Circuit Discovery Mechanistic Interpretability Causal Interpretability Explainability Evaluation

May 25, 2026cs.LG

MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability

Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it. Automated methods have made this search systematic, but each one starts afresh for every behaviour, and the effort spent finding one circuit does nothing for the next. Circuit discovery has thus been automated, but not amortised. We ask whether circuit discovery can itself be learned. We frame it as a sequential decision problem over the computation graph of GPT-2 small, in which a policy removes edges until it reaches a compact subgraph that preserves the behaviour, guided by a faithfulness reward defined through causal intervention. A single policy trained across twelve behaviours recovers a faithful circuit for each, and once frozen it transfers to behaviours it never saw during training, recovering their known circuits without further search. A short warm-start improves these transferred circuits, returning far smaller ones than training from scratch. While the learned policy does not match a per-behaviour search on circuit size or cost, it shows that circuit discovery is a learnable, transferable procedure rather than a search repeated for every behaviour.

Barsat Khadka

School of Computing Sciences and Engineering The University of Southern Mississippi

Transformer Interpretability Circuit Discovery Mechanistic Interpretability Causal Interpretability

May 23, 2026cs.CL

CSP-Atlas: Concept-Specific Neural Circuits in a Sparse Python Transformer

A sparse 8-layer code transformer develops dedicated neural circuitry for every Python construct tested, and that circuitry is organised by a clean computational principle rather than by semantic category. We extract neural circuits for 106 concepts (43 AST node types, 63 builtin objects) by marginalising across 63,800 controlled prompts, and decompose each circuit into concept-specific and token-driven components using contrastive checker prompts that present a keyword token without its associated syntactic structure. Three findings emerge. First, all 106 concepts produce non-empty universal circuits at every one of nine parameter settings, and the ranking of concept-specificity across constructs is stable across the sweep - survival is not an artifact of a permissive threshold. Second, AST circuits contain a genuine concept component distinct from token activation: concept-only neurons constitute up to 62.5% of the loudest-firing neurons at mid-to-late layers, while builtin circuits are almost entirely token-driven. Third, six computationally atomic constructs - Import, ImportFrom, Break, Continue, Pass, Assert - cluster together despite being semantically unrelated, sharing only the property of being single-statement constructs requiring no nested body; this atomicity super-cluster, together with a four-tier hierarchy organised by token ambiguity and structural distinctiveness, shows that the model's internal organisation tracks computational structure rather than meaning. The methodology, full decomposition data, and analysis code are released.

Piotr Wilam

University College London

Transformer Interpretability Circuit Discovery Mechanistic Interpretability Circuits in Language Models Code Language Models

May 22, 2026cs.LG

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers

We present a three-step recipe for identifying attention-head circuits in pretrained transformers. A per-head spectral signal -- the time-integrated participation ratio of each head's attention output -- ranks heads doing sustained content-dependent computation without labels or attribution gradients. A task-pattern screen filters this general indicator into a task-specific candidate circuit, and group ablation against a matched-random control completes the causal claim. We validate across an 8x parameter range (51M to 1B-active / 7B-total), two architecture families (dense, mixture-of-experts), and four pretraining pipelines. The recipe ports: a 2-6 head induction circuit is causally necessary in every model tested, with a 94-100% drop in synthetic-induction top-1 after ablation. The spectral signal is predictive without supervision: on six independent seeds of a 51M-parameter probe model, the same computation identifies the seed-specific circuit on each seed. The fraction of heads doing identifiable specialized computation is conserved at 17-19% across the Pythia family (124M to 410M), while specific induction circuits stay 3-11 heads -- sublinear in total head count. This paper is the methodology anchor of a three-paper program; companion papers extend the recipe to developmental trajectories during pretraining and to composed-task circuits where pattern selectivity decouples from task-causal structure.

Yongzhong Xu

Transformer Interpretability Circuit Discovery Attention Head Analysis Self-Attention Mechanistic Interpretability Induction Heads+2

May 20, 2026cs.LG

From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach

Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no shared formal representation for what circuits compute, how they relate, or when two findings provide evidence for the same mechanism. This work provides a formal infrastructure for cumulative mechanistic science by treating circuit interpretation as inductive theory construction. Each circuit is characterised at two levels: a Causal Functional Signature (CFS), which grounds component behaviour in causal attribution evidence and token role profiles, and an architectural signature

τ_{\mathrm{arch}}

, learned by inductive logic programming (ILP) from scale-invariant structural predicates. Together, these constitute a formal coherence layer that makes mechanistic claims explicit, comparable via

θ

-subsumption, and portable across model scales. CFS reveals qualitatively distinct computational strategies across task types, including attention-mediated copying versus MLP-mediated binding. ILP signatures achieve substantially better structural separation than graph kernel and feature-vector baselines, and support principled transfer across model scales and architecture families.

Nura Aljaafari, Danilo S. Carvalho, Andre Freitas

Department of Computer Science, University of Manchester, United Kingdom · CRUK National Biomarker Centre, University of Manchester, United Kingdom · Idiap Research Institute, Switzerland

Circuit Discovery Mechanistic Interpretability Inductive Logic Programming Causal Interpretability

May 13, 2026cs.LG

Transformers Linearly Represent Highly Structured World Models

Do transformers, when trained on sequential reasoning traces, build internal models of the underlying task? And if so, does the structure of those internal representations mirror the structure of the domain? We train an 8-layer transformer on Sudoku solving traces and perform a mechanistic analysis of its internal computation. We establish two results. First, the model builds a substructure world model: it does not represent the board state cell by cell, as a human analyst would expect, but organizes information around the rows, columns, and boxes that Sudoku's constraints act on. Second, we identify a naked-single circuit: a small set of dedicated neurons in the final MLP layer, each individually detecting when exactly one digit remains possible for a specific cell, and reliably promoting that digit. These findings show that the geometry of an emergent world model is shaped by the constraint algebra of the domain, not its surface presentation, and that the resulting decision circuit is sparse, monosemantic, and fully interpretable. More broadly, they demonstrate that mechanistic interpretability tools can recover an end-to-end algorithmic account of how a transformer solves a combinatorial reasoning task.

Roman Kniazev, Nathanaël Fijalkow

LaBRI, CNRS · University of Bordeaux · France

Circuit Discovery World Models Mechanistic Interpretability Structured Reasoning Constraint Satisfaction Algorithmic Reasoning

May 12, 2026cs.CL

All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs

In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional Anisotropy Hypothesis: the idea that functions in large language models (LLMs) are localised to a unique or near-unique internal mechanism. We show that a single LLM task can instead be supported by multiple, structurally distinct circuits or sheaves that are simultaneously faithful, sparse, and complete. To systematically uncover such competing mechanisms, we introduce Overlap-Aware Sheaf Repulsion, a method that augments the CSD objective with an explicit penalty on structural overlap across multiple discovery runs, enabling the discovery of circuits or sheaves with strong task performance but minimal shared structure across a plethora of common CSD benchmarks. We find that this phenomenon becomes increasingly pronounced as the number of discovered sheaves grows and persists robustly across major CSD methods. We further identify an ultra-sparse three-edge sheaf and show that none of its edges is individually indispensable, undermining even weakened notions of canonical or essential components. To explain these findings, we propose a Distributive Dense Circuit Hypothesis and provide a theoretical analysis demonstrating that non-unique, low-overlap circuit explanations arise naturally from high-dimensional superposition under mild assumptions. Together, our results suggest that mechanistic explanations in LLMs are inherently non-canonical and call for a rethinking of how CSD results should be interpreted and evaluated.

Xi Chen, Mingyu Jin, Jingcheng Niu +7

University of Toronto · The Hong Kong University of Science and Technology (Guangzhou) · Rutgers University +2

Circuit Discovery LLM Interpretability Circuits in Language Models

May 9, 2026cs.AI

Data-driven Circuit Discovery for Interpretability of Language Models

Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph responsible for the LM's behavior. Existing circuit discovery methods are hypothesis-driven; they first informally define a task with a dataset, and then apply a circuit discovery algorithm over that dataset to obtain a single circuit. This imposes two strong assumptions: that the LM implements the task with a single circuit, and that the dataset adequately represents the task as humans understand it. We systematically test these assumptions across four previously studied tasks and find that even minor dataset variations that preserve task semantics can produce circuits with low edge overlap and cross-dataset faithfulness. More strikingly, when applied to a mixed dataset with two distinct tasks whose separately discovered circuits have near-zero cross-faithfulness, existing methods still return a single circuit with high faithfulness across both tasks. This indicates that current methods discover dataset-specific circuits, rather than general task circuits. We propose Data-driven Circuit Discovery (DCD), a new discovery framework that drops both assumptions: instead of returning a single circuit for a dataset, DCD first clusters examples in the dataset by how similarly the model processes them and discovers a separate circuit for each group. This allows distinct mechanisms to appear separately rather than merged into a single circuit; each circuit explains its group, not the full task. Experiments show that DCD discovers multiple circuits per dataset, each more faithful to its group than a single circuit discovered by existing methods. Broadly, DCD lets the data reveal mechanistic structure within LMs, rather than relying on human-defined task boundaries that may not align with how models organize their computation.

Daking Rai, Mor Geva, Ziyu Yao

George Mason University · Tel Aviv University

Circuit Discovery LLM Interpretability Circuits in Language Models

May 9, 2026cs.CL

Architecture, Not Scale: Circuit Localization in Large Language Models

Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention architecture matters more than parameter count. Studying three circuit types across Pythia and Qwen2.5, we find that grouped query attention produces circuits that are far more concentrated and mechanistically stable than standard multi-head attention at comparable scales. The same concentration pattern holds across indirect object identification, induction heads, and factual recall. Within a single architecture family (Qwen2.5), factual recall circuits undergo a discrete phase transition above a critical scale, collapsing to a single bottleneck rather than degrading gradually. These findings suggest that some architectural choices make large models more tractable to study and that interpretability difficulty is not a fixed consequence of model size.

Sohan Venkatesh

Manipal Institute of Technology Bengaluru.

Transformer Interpretability Grouped-Query Attention Circuit Discovery Attention Head Analysis Mechanistic Interpretability Circuits in Language Models

May 8, 2026cs.CL

How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits

The circuits framework in mechanistic interpretability aims to identify sparse subgraphs of model components that are causally responsible for a behavior, typically evaluated by measuring necessity and sufficiency. But these criteria say little about whether a circuit consistently captures how a model performs a task, or if it is specific to that task. We study these two properties, consistency and specificity, across six tasks and five models, extracting circuits at the component level (attention heads and MLP blocks) and at the level of individual MLP neurons. We find that component-level circuits are highly consistent and causally important for most tasks, but they are not specific: for a given task, ablating its own circuit drops accuracy by about as much as ablating another task's circuit. Neuron-level circuits, on the other hand, exhibit higher specificity across tasks, but far less consistency within tasks. This is explained by circuit overlap: component-level circuits share most of their components across tasks, related or not, while neuron-level circuits overlap only between closely related tasks. In a case study of the components shared by the task circuits of Llama-3.2-3B, we show that they consist mostly of MLP blocks, while the few attention heads within turn out to have general-purpose roles. Overall, our findings raise questions about the degree to which circuits can support targeted understanding of, and intervention on, model behavior.

Michael Li, Nishant Subramani

Carnegie Mellon University · Work done while at Carnegie Mellon University. · Northeastern University +1

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Causal Interventions in Language Models

Apr 27, 2026cs.AI

Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacity has been hindered by the vast complexity gap between scientific discovery and real-world engineering. We introduce SciCrafter, a Minecraft-based benchmark that operationalizes this loop through parameterized redstone circuit tasks. Agents must ignite lamps in specified patterns (e.g., simultaneously or in timed sequences); scaling target parameters substantially increases construction complexity and required knowledge, forcing genuine discovery rather than reliance on memorized solutions. Evaluating frontier models including GPT-5.2, Gemini-3-Pro, and Claude-Opus-4.5 under a general-purpose code agent scaffold, we find that all plateau at approximately 26% success rate. To diagnose these failures, we decompose the loop into four capacities--knowledge gap identification, experimental discovery, knowledge consolidation, and knowledge application--and design targeted interventions whose marginal contributions serve as proxies for corresponding gaps. Our analysis reveals that although the general knowledge application capability still remains as the biggest gap across all models, for frontier models the knowledge gap identification starts to become a major hurdle--indicating the bottleneck is shifting from solving problems right to raising the right problems for current AI. We release SciCrafter as a diagnostic probe for future research on AI systems that navigate the full discovery-to-application loop.

Zhou Ziheng, Huacong Tang, Jinyuan Zhang +9

University of California, Los Angeles · Peking University · Amazon

AI Agents for Scientific Discovery Circuit Discovery Causal Discovery AI Agent Benchmarks

Apr 18, 2026cs.CL

Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution

Existing feature-interpretation pipelines typically operate on uniformly sampled units or exhaustive feature sets, incurring massive costs on units irrelevant to target behaviors. To address this, we introduce the first CLT-native end-to-end pruning framework, PIE, which pioneers the paradigm of pruning first and interpreting later. PIE connects Pruning, automatic Interpretation, and interpretation Evaluation, establishing a comprehensive benchmarking environment to systematically measure behavioral fidelity and downstream interpretability under pruning. Within this framework, we adapt strong relevance baselines and propose Feature Attribution Patching (FAP), a patch-grounded attribution method that scores CLT features by aggregating gradient-weighted write contributions. Furthermore, we introduce FAP-Synergy, a systematic synergy-aware reranking procedure. We evaluate pruning using KL-divergence behavior retention and assess interpretation quality with FADE-style metrics across IOI and Doc-String datasets. Across budget constraints of K in {50, 100, 200, 400, 800}, our rigorous benchmarking reveals distinct operational regimes: while base FAP and adapted baselines perform robustly at relaxed budgets, FAP-Synergy excels in highly constrained, strict-budget regimes. Crucially, we demonstrate a practical "Effective Budget" advantage: on the IOI task for both Llama-3.2-1B and Gemma-2-2B, FAP-Synergy at K=50 functionally matches the behavioral fidelity of baseline circuits at K=75. Because downstream evaluation costs scale linearly per feature, Synergy effectively grants the pipeline 25 "free" features, achieving K=75 fidelity while reducing interpretation costs by 33%.

Qinhao Chen, Linyang He, Nima Mesgarani

Columbia University

LLM Pruning Feature Attribution Circuit Discovery Mechanistic Interpretability Explainability Evaluation

Jan 13, 2026cs.CL

Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages

Existing circuit discovery methods rely on templated tasks with clean counterfactuals, limiting their use on diverse natural text. We adapt Contextual Decomposition for Transformers (CD-T) for unstructured settings via label-balanced activation means and task-directional relevance scoring, enabling counterfactual-free circuit discovery. We leverage the discovered circuits for Circuit-Targeted Supervised Fine-Tuning (CT-SFT), restricting parameter updates to task-relevant heads and LayerNorm. Experiments on NusaX cross-lingual sentiment transfer show that CT-SFT is highly competitive for low-resource adaptation. While non-circuit sparse updates and full fine-tuning sometimes match target accuracy through capacity recruitment, CT-SFT most consistently avoids catastrophic forgetting, preserving source-language and related-task performance. Extensions to XNLI support the source-retention and intervention findings on a harder task and two model families, showing that circuit-targeted adaptation provides a more controlled, intervention-supported alternative to global fine-tuning.

Khumaisa Nur'aini, Ayu Purwarianti, Alham Fikri Aji +1

Monash University Indonesia · MBZUAI · Institute Teknologi Bandung +1

Selective Fine-Tuning Circuit Discovery Cross-Lingual Transfer Mechanistic Interpretability Low-Resource Language Processing Catastrophic Forgetting