EleutherAI / delphiLinks
Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.
☆206Updated this week
Alternatives and similar repositories for delphi
Users that are interested in delphi are comparing it to the libraries listed below
Sorting:
- ☆111Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- ☆184Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆211Updated 8 months ago
- ☆162Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- ☆52Updated 9 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆126Updated last year
- ☆237Updated 10 months ago
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- ☆327Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆122Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated last month
- ☆103Updated 6 months ago
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- ☆90Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆176Updated 4 months ago
- Sparsify transformers with SAEs and transcoders☆608Updated this week
- Modified to support crosscoder training.☆21Updated 3 weeks ago
- ☆66Updated last week
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆143Updated last week
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- [ICLR 2025] General-purpose activation steering library☆94Updated 3 weeks ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆257Updated 2 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆197Updated 9 months ago