English

Tracking Equivalent Mechanistic Interpretations Across Neural Networks

Machine Learning 2026-04-01 v1 Computation and Language

Abstract

Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that task. However, MI is difficult to scale and generalize. This stems in part from two key challenges: there is no precise notion of a valid interpretation; and, generating interpretations is often an ad hoc process. In this paper, we address these challenges by defining and studying the problem of interpretive equivalence: determining whether two different models share a common interpretation, without requiring an explicit description of what that interpretation is. At the core of our approach, we propose and formalize the principle that two interpretations of a model are equivalent if all of their possible implementations are also equivalent. We develop an algorithm to estimate interpretive equivalence and case study its use on Transformer-based models. To analyze our algorithm, we introduce necessary and sufficient conditions for interpretive equivalence based on models' representation similarity. We provide guarantees that simultaneously relate a model's algorithmic interpretations, circuits, and representations. Our framework lays a foundation for the development of more rigorous evaluation methods of MI and automated, generalizable interpretation discovery methods.

Keywords

Cite

@article{arxiv.2603.30002,
  title  = {Tracking Equivalent Mechanistic Interpretations Across Neural Networks},
  author = {Alan Sun and Mariya Toneva},
  journal= {arXiv preprint arXiv:2603.30002},
  year   = {2026}
}

Comments

32 pages, 5 figures, ICLR 2026

R2 v1 2026-07-01T11:46:43.725Z