Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

OhhMoo
/
sae-rl-qwen05b-layers

Feature Extraction
PyTorch
English
sparse-autoencoder
sae
topk-sae
interpretability
mechanistic-interpretability
ppo
rlhf
reasoning
training-dynamics
qwen
qwen2.5
Model card Files Files and versions
xet
Community
sae-rl-qwen05b-layers
3.81 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 22 commits
OhhMoo's picture
OhhMoo
explain what each chain tests and the three-chain design logic
b9ce331 verified 12 days ago
  • results
    Replace stale Apr 23 plots with sae_eval.csv (honest val) 15 days ago
  • sae_flexible
    add flexible chain at canonical path (mirrors layer*/ folders during migration) 12 days ago
  • sae_kl0p025
    add kl=0.025 sweep chain 12 days ago
  • sae_strict
    add strict L23 k=256 retrain 12 days ago
  • .gitattributes
    1.52 kB
    initial commit 22 days ago
  • README.md
    10.5 kB
    explain what each chain tests and the three-chain design logic 12 days ago
  • loader.py
    1.83 kB
    Upload folder using huggingface_hub 22 days ago