saev - Sparse Auto-Encoders for Vision

Sparse autoencoders (SAEs) for vision transformers (ViTs), implemented in PyTorch.

This is the framework used for our preprint "Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models"

• arXiv preprint
• Huggingface Models
• API Docs
• Demos

Saev is a framework for training sparse autoencoders (SAEs) on vision transformers (ViTs) in PyTorch.

Docs

• Docs
• Quickstart
• Using saev
• API reference

See the docs for an overview.

You can ask questions about this repo using the llms.txt file.

Example (macOS):

curl https://osu-nlp-group.github.io/saev/api/llms.txt | pbcopy, then paste into Claude or any LLM interface of your choice.