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

Understand

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 provide a comprehensive survey from a task-centric perspective, organizing the taxonomy of MI research around specific research questions or tasks.