Contrastive Sparse Auto-Encoders

non-profit

https://yp-edu.github.io/publications/lczero-planning

AI & ML interests

Chess interpretability

authored a paper 8 months ago

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning

Paper • 2502.00726 • Published Feb 2, 2025 • 1

updated a Space almost 2 years ago

Lczero Planning Demo

Explore chess features with FEN and game analysis

updated a model almost 2 years ago

lczero-planning/saes

Updated Jul 24, 2024

updated a Space almost 2 years ago

README

authored a paper almost 2 years ago

Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents

Paper • 2406.04028 • Published Jun 6, 2024 • 2

updated 3 datasets about 2 years ago

lczero-planning/features

Viewer • Updated May 20, 2024 • 185k • 26

lczero-planning/activations

Viewer • Updated May 20, 2024 • 641k • 238 • 1

lczero-planning/trajectories

Viewer • Updated May 10, 2024 • 110k • 74

updated a model about 2 years ago

lczero-planning/models-moved

Updated May 9, 2024

updated a dataset about 2 years ago

lczero-planning/boards

Viewer • Updated Apr 30, 2024 • 2.79M • 20 • 1