AlignmentResearch / tuned-lensLinks
Tools for understanding how transformer predictions are built layer-by-layer
☆514Updated 2 weeks ago
Alternatives and similar repositories for tuned-lens
Users that are interested in tuned-lens are comparing it to the libraries listed below
Sorting:
- ☆276Updated last year
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆793Updated 2 weeks ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆211Updated 8 months ago
- ☆237Updated 10 months ago
- Sparsify transformers with SAEs and transcoders☆608Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆630Updated this week
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated this week
- ☆223Updated last year
- ☆508Updated last year
- Erasing concepts from neural representations with provable guarantees☆232Updated 6 months ago
- Training Sparse Autoencoders on Language Models☆919Updated this week
- ☆162Updated 9 months ago
- ☆327Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year
- ☆126Updated last year
- ☆122Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆510Updated last year
- ☆111Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- ☆184Updated last month
- This repository collects all relevant resources about interpretability in LLMs☆368Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Locating and editing factual associations in GPT (NeurIPS 2022)☆657Updated last year
- Interpretability for sequence generation models 🐛 🔍☆433Updated 3 months ago
- Editing Models with Task Arithmetic☆494Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆542Updated 6 months ago