Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams

James Henry

cs.LGMay 25, 2026

Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams

Authors: James Henry

Organizations: Independent Researcher

Abstract

Concept probes extracted from transformer residual streams are only as reliable as the layer from which they are extracted. The common practice of probing at a fixed late layer or at the peak of a separation score function ignores a fundamental structural feature: concept representations undergo substantial directional rotation during their assembly phase, and do not settle into a stable direction until a characteristic handoff layer after the primary Concept Allocation Zone (CAZ). We introduce Geometric Evolution Maps (GEMs), which track the full directional trajectory of a concept through residual stream activations, identify the handoff layer where rotation ceases, and extract the settled probe direction from that layer. Across 23 architectures spanning 70M to 14B parameters and 17 concept types, the entry-to-exit cosine similarity within CAZs has a mean of 0.233, showing that probe direction at CAZ entry does not reliably predict probe direction at exit. Ablation experiments across 391 concept x model pairs (23 models x 17 concepts) show that GEM-extracted probes are at least as precise as peak-layer probes in 268/391 trials (68.5%), and strictly outperform in 259/391 (66.2%). The architecture split is pronounced: MHA models favour the handoff in 173/221 trials (78.3%); GQA models favour the handoff in only 56/119 trials (47.1%). Model-level Wilcoxon: W=214, N=23, p=0.010 (one-sided). An adaptive ablation width rule targets the 79/391 near-final-layer cases: it improves probe quality in 60/79 triggered cases (75.9%), mean gain +7.44pp. A direction-specificity control confirms the ablation effect is concept-direction specific: median 377x suppression rate versus random-direction ablation (99.1% of concept directions beat all 10 random seeds). Reference implementation: rosetta_tools v1.3.1 (doi:10.5281/zenodo.20361433).

Explore similar work

May 24, 2026cs.LG

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth

Concept formation in transformer language models is depth-extended, not a single-layer event: concepts emerge gradually across a contiguous region of the residual stream. Mechanistic interpretability methods identify the single layer of peak class separation -- the "best layer" -- capturing a snapshot rather than the process itself. We introduce the Concept Allocation Zone (CAZ): the depth interval within which a concept becomes measurably separable, the region allocated to its geometric expression. We formalize the CAZ through three layer-wise metrics (Separation, Concept Coherence, Concept Velocity) and derive principled boundary detection without manual layer sweeps. A CAZ is not a concept: it is the depth region within which the model organizes its geometry to make a concept separable. A single concept typically participates in multiple CAZes; multiple concepts may share one. Empirical validation across 34 models from 8 architectural families and 7 concepts reveals that the separation curve S(l) is frequently multimodal. A scored detector uncovers "gentle CAZes" -- subtle allocation regions invisible to standard peak detection but causally active in 93-100% of cases under ablation (16 of 34 models; 26 in the companion validation paper). The framework generates seven testable predictions; four yield clear verdicts (two not supported, one partially supported, one supported), one had its precondition invalidated by the data, and two are underpowered -- with cross-architecture alignment confirmed as depth-matched rather than monolithic under leave-one-concept-out cross-validation. Reference implementation: rosetta_tools v1.3.1 (doi:10.5281/zenodo.20361433).

James Henry

Transformer Architectures Model Activations Mechanistic Interpretability Narrative Coherence

Ask PDF

May 2, 2026cs.LG

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations

We test whether the causal inner product of \citet{park2024linear} -- defined by the unembedding covariance

Σ

-- enables cross-lingual concept transport. Across 17 models and 4 language pairs, a matched-spectrum randomization test finds that Whitened Causal Alignment is indistinguishable from spectral regularization alone (

p = 0.95

). However, this failure reveals a broader phenomenon: anti-concentration is observed in residual-stream difference-of-means vectors across five architecture families (

p < 10^{-33}

) and supported by SAE features (e.g.,

p = 4.5 \times 10^{-19}

) and linear probes on Gemma and Llama. We discover a \emph{dual geometry}: activation-space concept directions anti-concentrate in the spectral tail, while static unembedding-row contrasts \emph{concentrate} in high-variance directions (

p < 10^{-4}

). Split-injection causal interventions support the functional basis on Gemma and Llama (Cohen's

d

up to

1.80

), and POS-tag probing across 8 models shows syntax preferentially encodes in the high-variance subspace in 6 of 8 architectures (

p < 0.013

), with the Qwen~2.5 family showing a significant reversal consistent with architecture-specific spectral structure. These results suggest transformers may rotate semantic content into spectrally quiet regions during contextualized processing, encoding concepts where they can be manipulated with reduced grammatical disruption.

Pratyush Acharya, Nuraj Rimal, Habish Dhakal

Cross-Lingual Transfer Concentration Inequalities

Ask PDF

Sep 21, 2026cs.CL

The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts

The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-related linear structures are organized within the model. We propose the Answer-Basin Representation Hypothesis: the probability measure induced over answers by the model's continuation distribution organizes these linear structures, with its statistics represented along linear directions shared across questions. All continuations yielding the same answer form an answer basin, whose mass is their total probability. These basin masses define the pushforward probability measure over answers. We posit that concept-related linear structure emerges from differences in the answer measure rather than being determined by changes in concept labels. Experiments across models and tasks link concept-consistent effects and their reversals in probing and steering to the alignment between concept labels and the answer measure.

Manjiang Yu, Hongji Li, Zihan Wang +5

Topic pending

Ask PDF