cs.LGNov 2, 2026

Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models

Authors: Muhan Yeo, Bong Gyun Kang, HyunGi Kim, Sungroh Yoon

Organizations: Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea · McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA · UNIST InnoCORE AI-Space Solar Initiative, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea

Abstract

Deep learning models for electronic health records achieve strong predictive performance but provide little insight into what clinical concepts they represent internally. Post-hoc attribution methods produce per-cell importance scores that lack temporal coherence, cross-variable structure, and reusability across patients. We introduce the Temporal Island Sparse Autoencoder (TI-SAE), which learns a backbone-specific, patient-shared clinical concept dictionary from a frozen predictive model's representations. Each dictionary entry (latent) is defined by learned temporal Gaussian islands (specifying when the concept is active) and a sparse variable-composition vector (specifying which variables are involved). A decoupled selector then identifies which dictionary entries drive each patient's prediction, separating representation learning from attribution. We evaluate TI-SAE across five backbone architectures spanning different representation strategies on MIMIC-III and MIMIC-IV (three prediction tasks each). TI-SAE produces structured clinical concepts that go beyond transient attribution heatmaps while achieving strong performance on standard faithfulness benchmarks.

Figures & tables

Appendix figures & tables53 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 13, 2026

Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction

Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter autoregressive clinical sequence model, at all 10 residual stream extraction points on INSPECT (outpatient) and MIMIC-IV (ICU). SAE decomposition reveals progressive abstraction across transformer depth: layer-0 features are near-perfect token detectors (45.7% singleton), while layer-6 features span approximately 30 token types across multiple clinical categories (0.5% singleton). Under full-sequence simple linear probes, SAE features outperform dense representations for discrete event prediction (mortality) while dense representations outperform for continuous magnitude prediction (length of stay) - a probe-level representational phenomenon that does not extend to clinically relevant leakage-safe windows, where dense representations match or exceed SAE features across all tested settings (eICU-CRD 48-hour AUC: SAE 0.871 versus dense 0.880; base model zero-shot, SAE dictionaries trained on eICU activations; MIMIC-IV: 0.836 versus 0.914; INSPECT 1-year/3-year: 0.697 versus 0.800). A delta-mode intervention method reduces SAE perturbation noise by 86x, enabling cleaner feature-level experiments, though the resulting perturbation effects are larger than random controls in 3 of 4 conditions but not formally significant. Feature reproducibility across random seeds is 21%, and individual features should be interpreted as illustrative rather than stable.
Oct 4, 2026

TSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models

Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns models rely on is essential for assessing reliability and identifying failures. Input attribution identifies important variables and time segments but offers limited insight into internal features, while standard sparse autoencoder (SAE) objectives do not directly constrain cross-variable structure or temporal continuity. We introduce TSAE, a structured sparse autoencoder for forecasting representations that decomposes hidden states into individually inspectable features. TSAE organizes cross-variable structure through shared and variable-routed private dictionaries, separates feature detection from magnitude estimation with gated encoding, and constrains neighboring sparse-code changes according to raw-segment similarity. These mechanisms support analysis of variable context, activation strength, and temporal evolution. Forecast-consistency fine-tuning further improves preservation of the frozen forecaster's outputs. The accompanying TSEVAL protocol separately audits fidelity, feature coherence, and physical calibration to ground feature interpretation. In three-seed experiments with frozen PatchTST on ETTh1, ETTh2, and ETTm1, TSAE achieves the lowest hidden-state reconstruction error, normalized forecast-reconstruction error (NFRE), and feature transition rate among five SAEs at comparable per-token activity. NFRE decreases by 4.3-26.4% relative to the next-best mean. Dataset-dependent tradeoffs in selectivity, physical correlation, and calibration show that fidelity and temporal-stability gains require independent semantic validation to support feature interpretation.
Mar 10, 2026

Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models

Time series foundation models (TSFMs) are increasingly deployed in high-stakes domains, yet their internal representations remain opaque. We present the first application of sparse autoencoders (SAEs) to a TSFM, training TopK SAEs on activations of Chronos-T5-Large (710M parameters) across six layers. Through 392 single-feature ablation experiments, we establish that every ablated feature produces a positive CRPS degradation, confirming causal relevance. Our analysis reveals a depth-dependent hierarchy: early encoder layers encode low-level frequency features, the mid-encoder concentrates causally critical change-detection features, and the final encoder compresses a rich but less causally important taxonomy of temporal concepts. The most critical features reside in the mid-encoder (max single-feature Delta CRPS = 38.61), not in the semantically richest final encoder layer, where progressive ablation paradoxically improves forecast quality. These findings demonstrate that mechanistic interpretability transfers effectively to TSFMs and that Chronos-T5 relies on abrupt-dynamics detection rather than periodic pattern recognition.