EleutherAI / concept-erasureLinks
Erasing concepts from neural representations with provable guarantees
☆231Updated 6 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:
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- ☆124Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆274Updated last year
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- Utilities for the HuggingFace transformers library☆70Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- ☆234Updated 10 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- git extension for {collaborative, communal, continual} model development☆217Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- ☆104Updated 5 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆186Updated 2 years ago
- ☆136Updated 4 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆28Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Code repository for the c-BTM paper☆107Updated last year
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆100Updated last month
- Attribution-based Parameter Decomposition☆28Updated last month
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆200Updated 2 years ago
- ☆121Updated last year
- ☆83Updated last year