JoshEngels / SAE-Dark-MatterLinks
Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"
☆23Updated 6 months ago
Alternatives and similar repositories for SAE-Dark-Matter
Users that are interested in SAE-Dark-Matter are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆120Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆202Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆210Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆74Updated 3 weeks ago
- ☆122Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆16Updated 7 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 8 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆21Updated 3 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆23Updated 3 months ago
- ☆234Updated 10 months ago
- Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"☆26Updated 4 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆157Updated 8 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆113Updated last year
- ☆89Updated last year
- ☆104Updated 6 months ago
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆195Updated 9 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆23Updated 6 months ago
- Steering Llama 2 with Contrastive Activation Addition☆170Updated last year
- ☆125Updated last year
- ☆109Updated 3 weeks ago