EleutherAI / elkLinks
Keeping language models honest by directly eliciting knowledge encoded in their activations.
☆209Updated last week
Alternatives and similar repositories for elk
Users that are interested in elk are comparing it to the libraries listed below
Sorting:
- Erasing concepts from neural representations with provable guarantees☆238Updated 8 months ago
- ☆304Updated last year
- ☆279Updated last year
- Mechanistic Interpretability Visualizations using React☆293Updated 10 months ago
- ☆128Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆247Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆94Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆532Updated 2 months ago
- 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
- A toolkit for describing model features and intervening on those features to steer behavior.☆207Updated 11 months ago
- A dataset of alignment research and code to reproduce it☆78Updated 2 years ago
- METR Task Standard☆163Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- ☆29Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- ☆113Updated last week
- ☆142Updated last month
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- ☆126Updated last year
- ☆109Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- ☆59Updated 3 weeks ago