A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i
Year: 2025
Type: preprint
Abstract: Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because neural networks contain implicit explanations which can be extracted and understood. We hence show that Explanatory Faithfulness, an assessment of how well an explanation fits a model, is well-defined. We propose a definition of Mechanistic Interpretability (MI) as the practice of producing Model-level, Ontic, Causal-Mechanistic, and Falsifiable explanations of neural networks, allowing us to distinguish MI from other interpretability paradigms and detail MI's inherent limits. We formulate the Principle of Explanatory Optimism, a conjecture which we argue is a necessary precondition for the success of Mechanistic Interpretability.
Source: arXiv (Cornell University)
Authors: Ayonrinde, Kola, Jaburi, Louis
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414769259