EleutherAI / elkLinks
Keeping language models honest by directly eliciting knowledge encoded in their activations.
☆207Updated 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☆231Updated 6 months ago
- ☆285Updated last year
- ☆274Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆184Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- ☆233Updated 10 months ago
- ☆123Updated last year
- Utilities for the HuggingFace transformers library☆70Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- ☆28Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆85Updated last year
- 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
- A dataset of alignment research and code to reproduce it☆77Updated 2 years 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
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 9 months ago
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- ☆121Updated 11 months ago
- METR Task Standard☆154Updated 5 months ago
- Measuring the situational awareness of language models☆37Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆195Updated 8 months ago
- ☆137Updated last week
- ☆134Updated 4 months ago
- ☆94Updated 3 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago