analiza aiqbench
This research addresses a critical gap in mechanistic interpretability by introducing the Geometry-Adaptive Explainer (GAE), which maintains causal faithfulness when models encounter out-of-distribution data shifts. The method geometrically realigns dictionary-based explainers with rotated activation subspaces without requiring gradient updates or labeled data, offering a robust solution for analyzing model behavior under distributional changes.
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
arXiv:2605.21849v2 Announce Type: replace-cross Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Computation and Language (cs.CL)
arXiv:2605.21849 [cs.LG]
(or arXiv:2605.21849v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.21849 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 254 cuvinte