Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
whitepenguin
/
gpt2-medium-bLM100M-SAE
like
0
English
sae-lens
sparse-autoencoder
mechanistic-interpretability
gpt2-medium
babylm
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
gpt2-medium-bLM100M-SAE
/
layer_22
Ctrl+K
Ctrl+K
1 contributor
History:
9 commits
whitepenguin
Fix layer 22: proper BatchTopK → JumpReLU conversion
9d58948
verified
4 months ago
activation_scaler.json
Safe
24 Bytes
Add layer_22/activation_scaler.json
4 months ago
activations_store_state.safetensors
88 Bytes
xet
Add layer_22/activations_store_state.safetensors
4 months ago
cfg.json
684 Bytes
Fix layer 22: proper BatchTopK → JumpReLU conversion
4 months ago
runner_cfg.json
2.53 kB
Add layer_22/runner_cfg.json
4 months ago
sae_weights.safetensors
134 MB
xet
Fix layer 22: proper BatchTopK → JumpReLU conversion
4 months ago
sparsity.safetensors
65.6 kB
xet
Add layer_22/sparsity.safetensors
4 months ago
