Mechanist Interpretability for Alignment Algorithms

AI & ML interests

AI Safety, Mechanist Interpretability

Recent Activity

ishangarg183  updated a dataset 5 days ago

MInAlA/crosscoder-multilayer-split-activations

ishangarg183  published a dataset 11 days ago

MInAlA/crosscoder-multilayer-split-activations

ishangarg183  updated a dataset 16 days ago

MInAlA/crosscoder-smollm3-ppo

View all activity

Team members 5