EleutherAI / concept-erasureLinks
Erasing concepts from neural representations with provable guarantees
☆236Updated 8 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:
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated 2 weeks ago
- ☆127Updated last year
- ☆276Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆530Updated last month
- ☆242Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated this week
- ☆109Updated 7 months ago
- ☆142Updated 3 weeks ago
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆291Updated 9 months ago
- ☆29Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- git extension for {collaborative, communal, continual} model development☆215Updated 10 months ago
- ☆83Updated last year
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- ☆81Updated 7 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆124Updated 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
- Mechanistic Interpretability for Transformer Models☆53Updated 3 years ago
- Tools for studying developmental interpretability in neural networks.☆105Updated 3 months ago
- How do transformer LMs encode relations?☆53Updated last year
- RuLES: a benchmark for evaluating rule-following in language models☆234Updated 7 months ago