A compilation of sparse auto-encoders trained on large language models.
David Louapre
dlouapre
AI & ML interests
Large Language Models, Mechanistic Interpretability, ML & Games, Education
Recent Activity
updated
a collection
5 days ago
Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability
updated
a collection
5 days ago
Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability
updated
a collection
5 days ago
Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability
Organizations
models
6
dlouapre/SmolChessLM_780k_30Mg
Text Generation
•
0.0B
•
Updated
•
56
dlouapre/SmolChessLM_6M_30Mg
Text Generation
•
0.0B
•
Updated
•
100
dlouapre/uci_tokenizer_pairs
Updated
dlouapre/uci_tokenizer_single
Updated
dlouapre/chess_tokenizer_pairs
Updated
dlouapre/chess_tokenizer_single
Updated
datasets
8
dlouapre/lichess_2025-01_30M
Viewer
•
Updated
•
30M
•
119
dlouapre/lichess_2025-01_10M
Viewer
•
Updated
•
10M
•
90
dlouapre/lichess_2025-01_3M
Viewer
•
Updated
•
3M
•
80
dlouapre/lichess_2025-01_1M
Viewer
•
Updated
•
1M
•
96
dlouapre/lichess_2025-08_10k
Viewer
•
Updated
•
10k
•
146
dlouapre/lichess_2025-01_10k
Viewer
•
Updated
•
10k
•
87
dlouapre/lichess_2025-01_100k
Viewer
•
Updated
•
100k
•
94
dlouapre/lichess_2025-01_30k
Viewer
•
Updated
•
30k
•
126