Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
tim-lawson
's Collections
Learning to Skip the Middle Layers of Transformers
Multi-Layer SAEs
Multi-Layer SAEs with Tuned Lens
Multi-Layer SAEs with Transformers
Multi-Layer SAEs with Tuned Lens and Transformers
Single-Layer SAEs
Single-Layer SAEs with Transformers
timkl
timkl
updated
Sep 30, 2025
Upvote
-
tim-lawson/gpt2_c4
Updated
Sep 25, 2025
•
3
tim-lawson/gpt2_fineweb
Updated
Sep 25, 2025
•
31
tim-lawson/gpt2_openwebtext
Updated
Sep 25, 2025
•
2
tim-lawson/gpt2_pile
Updated
Sep 25, 2025
•
2
tim-lawson/gpt2_slimpajama
Updated
Sep 25, 2025
•
4
tim-lawson/pretrain_gpt2_c4
0.1B
•
Updated
Sep 25, 2025
•
1
tim-lawson/pretrain_gpt2_fineweb
0.1B
•
Updated
Sep 25, 2025
•
1
tim-lawson/pretrain_gpt2_openwebtext
0.1B
•
Updated
Sep 25, 2025
•
1
tim-lawson/gemma3_pile
Updated
Sep 26, 2025
•
2
tim-lawson/gemma3_c4_kl_270m_4b-pt
Updated
Sep 28, 2025
•
2
tim-lawson/gemma3_fineweb_kl_1b-pt_4b-pt
Updated
Sep 28, 2025
•
2
tim-lawson/gemma3_fineweb_kl_270m_1b-pt
Updated
Sep 28, 2025
•
3
tim-lawson/gemma3_pile_kl_270m_1b-pt
Updated
Sep 29, 2025
•
4
tim-lawson/gemma3_c4
Updated
Sep 27, 2025
•
2
tim-lawson/gemma3_c4_kl_270m_1b-pt
Updated
Sep 27, 2025
•
3
tim-lawson/gemma3_c4_kl_1b-pt_4b-pt
Updated
Sep 28, 2025
•
2
tim-lawson/gemma3_fineweb_kl_270m_4b-pt
Updated
Sep 28, 2025
•
2
tim-lawson/gemma3_fineweb
Updated
Sep 26, 2025
•
2
tim-lawson/gemma3_slimpajama_kl_270m_1b-pt
Updated
Sep 29, 2025
•
2
tim-lawson/gemma3_openwebtext_kl_270m_1b-pt
Updated
Sep 29, 2025
•
2
tim-lawson/gemma3_slimpajama
Updated
Sep 26, 2025
•
6
tim-lawson/gemma3_openwebtext
Updated
Sep 26, 2025
•
16
tim-lawson/gemma3_openwebtext_kl_270m_4b-pt
Updated
Sep 30, 2025
•
3
tim-lawson/gemma3_pile_kl_1b-pt_4b-pt
Updated
Sep 30, 2025
•
3
tim-lawson/gemma3_pile_kl_270m_4b-pt
Updated
Sep 30, 2025
•
4
tim-lawson/gemma3_openwebtext_kl_1b-pt_4b-pt
Updated
Sep 30, 2025
•
3
tim-lawson/gemma3_slimpajama_kl_1b-pt_4b-pt
Updated
Sep 30, 2025
•
1
tim-lawson/gemma3_slimpajama_kl_270m_4b-pt
Updated
Sep 30, 2025
•
2
tim-lawson/gpt2_fineweb_kl_small_xl
Updated
Sep 26, 2025
•
1
tim-lawson/gpt2_c4_kl_small_large
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_c4_kl_small_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_c4_kl_small_medium
Updated
Sep 25, 2025
•
27
tim-lawson/gpt2_openwebtext_kl_medium_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_c4_kl_medium_large
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_c4_kl_medium_xl
Updated
Sep 26, 2025
•
7
tim-lawson/gpt2_fineweb_kl_large_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_fineweb_kl_medium_large
Updated
Sep 26, 2025
•
3
tim-lawson/gpt2_openwebtext_kl_large_xl
Updated
Sep 26, 2025
•
3
tim-lawson/gpt2_fineweb_kl_medium_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_c4_kl_large_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_openwebtext_kl_medium_large
Updated
Sep 25, 2025
•
8
tim-lawson/gpt2_openwebtext_kl_small_large
Updated
Sep 26, 2025
•
3
tim-lawson/gpt2_openwebtext_kl_small_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_pile_kl_large_xl
Updated
Sep 26, 2025
•
19
tim-lawson/gpt2_slimpajama_kl_medium_xl
Updated
Sep 26, 2025
•
3
tim-lawson/gpt2_fineweb_kl_small_large
Updated
Sep 25, 2025
•
2
tim-lawson/gpt2_fineweb_kl_small_medium
Updated
Sep 25, 2025
•
2
tim-lawson/gpt2_slimpajama_kl_small_xl
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_slimpajama_kl_small_large
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_pile_kl_small_xl
Updated
Sep 26, 2025
•
6
tim-lawson/gpt2_pile_kl_medium_large
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_openwebtext_kl_small_medium
Updated
Sep 25, 2025
•
2
tim-lawson/gpt2_slimpajama_kl_large_xl
Updated
Sep 26, 2025
•
3
tim-lawson/gpt2_slimpajama_kl_medium_large
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_pile_kl_small_medium
Updated
Sep 26, 2025
•
3
tim-lawson/gpt2_slimpajama_kl_small_medium
Updated
Sep 26, 2025
•
2
tim-lawson/gpt2_pile_kl_medium_xl
Updated
Sep 26, 2025
•
4
tim-lawson/gpt2_pile_kl_small_large
Updated
Sep 26, 2025
•
1
Upvote
-
Share collection
View history
Collection guide
Browse collections