A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models

원문 초록

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for interpreting transformer-based language models (LMs), resulting in many novel insights yet introducing new challenges. However, there has not been work that comprehensively reviews these insights and challenges, particularly as a guide for newcomers to this field. To fill this gap, we present a comprehensive survey outlining fundamental objects of study in MI, techniques that have been used for its investigation, approaches for evaluating MI results, and significant findings and applications stemming from the use of MI to understand LMs. In particular, we present a roadmap for beginners to navigate the field and leverage MI for their benefit. Finally, we also identify current gaps in the field and discuss potential future directions.