AlignmentResearch / tuned-lensLinks
Tools for understanding how transformer predictions are built layer-by-layer
☆527Updated last month
Alternatives and similar repositories for tuned-lens
Users that are interested in tuned-lens are comparing it to the libraries listed below
Sorting:
- ☆242Updated last year
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆813Updated last month
- Sparsify transformers with SAEs and transcoders☆629Updated last week
- ☆276Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- ☆230Updated last year
- ☆127Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆270Updated last year
- ☆521Updated last year
- ☆123Updated last year
- ☆173Updated 10 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- ☆347Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆213Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆268Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆672Updated last week
- Training Sparse Autoencoders on Language Models☆977Updated this week
- Erasing concepts from neural representations with provable guarantees☆237Updated 8 months ago
- ☆125Updated 2 weeks ago
- 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
- ☆186Updated 2 months ago
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆516Updated last year
- Editing Models with Task Arithmetic☆503Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- This repository collects all relevant resources about interpretability in LLMs☆373Updated 11 months ago
- Interpretability for sequence generation models 🐛 🔍☆438Updated 2 weeks ago