EleutherAI / elkLinks
Keeping language models honest by directly eliciting knowledge encoded in their activations.
☆204Updated this 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☆227Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- ☆273Updated 11 months ago
- ☆222Updated 8 months ago
- ☆268Updated last year
- ☆121Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆76Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆125Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆493Updated 11 months ago
- Inspecting and Editing Knowledge Representations in Language Models☆116Updated last year
- A dataset of alignment research and code to reproduce it☆77Updated last year
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆131Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- METR Task Standard☆147Updated 3 months ago
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆70Updated 2 years ago
- ☆27Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated this week
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆181Updated last year
- Utilities for the HuggingFace transformers library☆68Updated 2 years ago
- ☆116Updated 9 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- ☆96Updated 3 months ago
- ☆236Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆90Updated 4 months ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- Measuring the situational awareness of language models☆35Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆213Updated last year