jannik-brinkmann / hugginglensLinks
TransformerLens + HuggingFace
☆11Updated last year
Alternatives and similar repositories for hugginglens
Users that are interested in hugginglens are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆100Updated last month
- Mechanistic Interpretability Visualizations using React☆273Updated 7 months ago
- ☆234Updated 10 months ago
- ☆125Updated last year
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆210Updated 7 months ago
- ☆326Updated 3 weeks ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆622Updated last week
- (Model-written) LLM evals library☆18Updated 7 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆221Updated last year
- Erasing concepts from neural representations with provable guarantees☆232Updated 6 months ago
- ☆28Updated last year
- ☆15Updated 4 months ago
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 2 years ago
- ☆109Updated 3 weeks ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆292Updated 2 weeks ago
- we got you bro☆36Updated last year
- Machine Learning for Alignment Bootcamp☆76Updated 3 years ago
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- ☆122Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Modified to support crosscoder training.☆21Updated 2 weeks ago
- The Happy Faces Benchmark☆15Updated 2 years ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆274Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year