collin-burns / discovering_latent_knowledge
☆264Updated last year
Alternatives and similar repositories for discovering_latent_knowledge:
Users that are interested in discovering_latent_knowledge are comparing it to the libraries listed below
- Mechanistic Interpretability Visualizations using React☆241Updated 4 months ago
- ☆121Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆486Updated 10 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆194Updated 4 months ago
- Using sparse coding to find distributed representations used by neural networks.☆236Updated last year
- ☆218Updated 6 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆199Updated this week
- ☆114Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆519Updated this week
- Erasing concepts from neural representations with provable guarantees☆227Updated 2 months ago
- ☆161Updated 2 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆241Updated 9 months ago
- ☆85Updated last week
- ☆104Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆169Updated this week
- ☆274Updated 2 months ago
- Tools for studying developmental interpretability in neural networks.☆88Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆144Updated 11 months ago
- ☆91Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆95Updated 2 months ago
- ☆202Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆481Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆180Updated last year
- Utilities for the HuggingFace transformers library☆67Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆209Updated last year
- Sparse Autoencoder Training Library☆48Updated 5 months ago
- ☆90Updated 2 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆548Updated this week
- ☆82Updated 8 months ago