collin-burns / discovering_latent_knowledgeLinks
☆276Updated 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
Sorting:
- ☆126Updated last year
- ☆238Updated 10 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆516Updated 2 weeks ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆212Updated 8 months ago
- ☆122Updated last year
- Erasing concepts from neural representations with provable guarantees☆232Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- ☆114Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated last week
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆188Updated 2 years ago
- Utilities for the HuggingFace transformers library☆70Updated 2 years ago
- ☆103Updated 6 months ago
- ☆327Updated this week
- ☆184Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- ☆223Updated last year
- ☆162Updated 9 months ago
- Sparsify transformers with SAEs and transcoders☆609Updated last week
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- ☆81Updated 6 months ago
- ☆105Updated 6 months ago
- ☆291Updated last year
- Sparse probing paper full code.☆59Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- ☆90Updated last year