search

ai-safety-foundation / sparse_autoencoder

Sparse Autoencoder for Mechanistic Interpretability
https://ai-safety-foundation.github.io/sparse_autoencoder/
MIT License
171 stars 39 forks source link

Resolved import error with PyTorch >= 2.2 #207

Open HuFY-dev opened 5 months ago

HuFY-dev commented 5 months ago

Renamed and hard-coded ParamsT (CamelCase for better style) to avoid importing inconsistencies between PyTorch 2.1 and PyTorch 2.2.