Sungjun Lim, Heedong Kim, Andrew Lee, Kyungwoo Song
Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainers such as sparse autoencoders and transcoders are a primary tool, but their faithfulness under out-of-distribution (OOD) shift has received little systematic attention. We show that distribution shift rotates the subspace that the model actively uses, misaligning the explainer's dictionary trained on in-distribution (ID) activations. We formalize this misalignment as the faithfulness gap, a geometric distance between the ID dictionary and the OOD-active subspace, and show that it bounds excess OOD projection loss. To reduce this gap, we propose the Geometry-Adaptive Explainer (GAE), which realigns the dictionary with the OOD-active subspace while preserving the original sparse feature activations. This requires only unlabeled OOD activations and no gradient updates. For the adapted dictionary, we also bound the excess projection loss caused by any remaining faithfulness gap. Empirically, GAE even matches or surpasses all training-based baselines in causal faithfulness across multiple models and OOD settings.
Aaron Mueller Boston University, Andrew Lee School of Engineering and Applied Sciences, Harvard University, Shruti Joshi Université de Montréal, Ekdeep Singh Lubana Goodfire AI, Dhanya Sridhar, Patrik Reizinger Eberhard-Karls-Universität Tübingen
A goal of interpretability is to recover disentangled representations of latent concepts (features) from the activations of neural networks. The quality of features is typically evaluated in isolation, and under implicit independence assumptions that may not hold in practice. Thus, it is unclear to what extent common featurization methods such as sparse autoencoders (SAEs) and probes disentangle one concept from another. We propose a multi-concept evaluation setting using concepts such as sentiment, domain, voice, and tense. We evaluate how well featurizers produce disentangled representations of each concept, observing that features are typically sensitive to only one concept, but also that concepts are distributed across many features. Then, we steer these features, measuring whether each concept is independently manipulable, and whether features interact. Even in idealized settings, steering a feature often affects many concepts, despite a near absence of interaction effects. These results suggest that correlational metrics are insufficient to establish steering selectivity, and that demonstrating that two features operate in separate spaces is insufficient to claim that they will be selective for one concept. These results underscore the importance of multi-concept evaluations in interpretability research.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Emergent Linear Representations in World Models of Self-Supervised Sequence Models
Neel Nanda, Andrew Lee, Martin Wattenberg
AI 速览：作者报告在自监督序列模型（如Othello棋类模型）的世界模型中发现棋盘状态的线性表示，并可通过向量算术控制模型行为。
How do sequence models represent their decision-making process? Prior work suggests that Othello-playing neural network learned nonlinear models of the board state (Li et al., 2023). In this work, we provide evidence of a closely related linear representation of the board. In particular, we show that probing for "my colour" vs. "opponent's colour" may be a simple yet powerful way to interpret the model's internal state. This precise understanding of the internal representations allows us to control the model's behaviour with simple vector arithmetic. Linear representations enable significant interpretability progress, which we demonstrate with further exploration of how the world model is computed.