Hakaze Cho

Mechanism of Task-oriented Information Removal in In-context Learning

Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis

Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insights

Binary Autoencoder for Mechanistic Interpretability of Large Language Models

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

Revisiting In-context Learning Inference Circuit in Large Language Models