Contrastive Sparse Auto-Encoders

AI & ML interests

Chess interpretability

Recent Activity

Xmaster6y  authored a paper 4 days ago

Policy Gradient Steering: Interventions from Behavioral Objectives

Xmaster6y  authored a paper about 1 year ago

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning

Xmaster6y  updated a Space about 2 years ago

lczero-planning/demo

View all activity

Team members 1