Understanding AI systems' inner workings is critical for ensuring value alignment and safety.
This review explores mechanistic interpretability: reverse-engineering the computational …

Grokking has been actively explored to reveal the mystery of delayed generalization.
Identifying interpretable algorithms inside the grokked models is a suggestive hint to …

Large language models (LLMs) demonstrate surprising capabilities, but we do not
understand how they are implemented. One hypothesis suggests that these capabilities are …