Hugging Face's logo

Solshine
/
deception-sae-nanochat-d20

deception-detection
sparse-autoencoders
mechanistic-interpretability
ai-safety
nanochat
Model card Files
xet
 Community
deception-sae-nanochat-d20

Commit History

Initial public release: SAE weights, cfg, and model card
ba67ba2

Solshine commited on