EleutherAI / elk
Keeping language models honest by directly eliciting knowledge encoded in their activations.
☆195Updated last week
Alternatives and similar repositories for elk:
Users that are interested in elk are comparing it to the libraries listed below
- ☆253Updated 7 months ago
- ☆262Updated 11 months ago
- Mechanistic Interpretability Visualizations using React☆232Updated 2 months ago
- Erasing concepts from neural representations with provable guarantees☆222Updated 3 weeks ago
- ☆203Updated 4 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆112Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆182Updated 2 months ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆71Updated last year
- ☆128Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆123Updated 8 months ago
- A dataset of alignment research and code to reproduce it☆73Updated last year
- ☆116Updated last year
- ☆25Updated 10 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆175Updated last year
- ☆109Updated 6 months ago
- Utilities for the HuggingFace transformers library☆64Updated 2 years ago
- Using sparse coding to find distributed representations used by neural networks.☆213Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆208Updated last year
- ☆52Updated this week
- ☆81Updated last week
- ☆55Updated 3 months ago
- ☆151Updated this week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆88Updated last year
- Tools for studying developmental interpretability in neural networks.☆84Updated 3 weeks ago
- A library for efficient patching and automatic circuit discovery.☆53Updated this week
- Tools for understanding how transformer predictions are built layer-by-layer☆475Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆88Updated this week
- Algebraic value editing in pretrained language models☆62Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆112Updated last year