EleutherAI / concept-erasureLinks
Erasing concepts from neural representations with provable guarantees
☆228Updated 4 months ago
Alternatives and similar repositories for concept-erasure
Users that are interested in concept-erasure are comparing it to the libraries listed below
Sorting:
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆202Updated 6 months ago
- ☆28Updated last year
- ☆121Updated last year
- ☆226Updated 8 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated 2 weeks ago
- Mechanistic Interpretability Visualizations using React☆257Updated 6 months ago
- ☆97Updated 4 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆500Updated last year
- Utilities for the HuggingFace transformers library☆68Updated 2 years ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- ☆134Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated this week
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆101Updated 3 weeks ago
- ☆82Updated 11 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- ☆270Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- How do transformer LMs encode relations?☆48Updated last year
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆197Updated 2 years ago
- git extension for {collaborative, communal, continual} model development☆213Updated 7 months ago
- ☆31Updated last year
- ☆57Updated 2 weeks ago
- 🧠 Starter templates for doing interpretability research☆70Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆500Updated last year
- ☆67Updated 2 years ago
- Using sparse coding to find distributed representations used by neural networks.☆255Updated last year