SAELens
English
sparse-autoencoder
SAE
interpretability
deception-detection
mechanistic-interpretability
neuronpedia
behavioral-sampling
phi
reasoning
Instructions to use Solshine/deception-saes-phi-4-mini-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use Solshine/deception-saes-phi-4-mini-reasoning with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 217a39c2718098c522f016679e1f1404afe47a8f2fd7b45b870cd31da4d0a52b
- Size of remote file:
- 302 MB
- SHA256:
- 7852a12a251f6aab9733ae151f7e567c3f2775e5a60ce439576e4811a923f413
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.