AlignmentResearch / tuned-lensLinks
Tools for understanding how transformer predictions are built layer-by-layer
☆532Updated 2 months ago
Alternatives and similar repositories for tuned-lens
Users that are interested in tuned-lens are comparing it to the libraries listed below
Sorting:
- ☆279Updated last year
- ☆247Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆819Updated last week
- Mechanistic Interpretability Visualizations using React☆293Updated 10 months ago
- Sparsify transformers with SAEs and transcoders☆640Updated last week
- Using sparse coding to find distributed representations used by neural networks.☆279Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆683Updated last week
- ☆128Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- ☆179Updated 11 months ago
- ☆530Updated last year
- Erasing concepts from neural representations with provable guarantees☆238Updated 8 months ago
- ☆354Updated 2 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆272Updated last year
- ☆234Updated last year
- Training Sparse Autoencoders on Language Models☆1,001Updated this week
- ☆131Updated this week
- ☆126Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆519Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- This repository collects all relevant resources about interpretability in LLMs☆375Updated 11 months ago
- ☆190Updated last week
- Editing Models with Task Arithmetic☆508Updated last year
- Locating and editing factual associations in GPT (NeurIPS 2022)☆675Updated last year
- ☆81Updated 7 months ago
- Interpretability for sequence generation models 🐛 🔍☆441Updated last month
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆552Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago