JoshEngels / SAE-Dark-MatterLinks
Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"
☆24Updated 10 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:
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆231Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆151Updated 5 months ago
- Sparse Autoencoder Training Library☆55Updated 7 months ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆28Updated 2 months ago
- Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"☆31Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆80Updated 4 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
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆130Updated 9 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"☆43Updated last year
- ☆111Updated 10 months ago
- Universal Neurons in GPT2 Language Models☆31Updated last year
- Code repo for the model organisms and convergent directions of EM papers.☆40Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆232Updated 11 months ago
- ☆132Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆27Updated 10 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated last year
- ☆136Updated 3 weeks ago
- ☆32Updated 9 months ago
- ☆95Updated last year
- Measuring the situational awareness of language models☆39Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆196Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆16Updated 11 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆93Updated last year
- PyTorch library for Active Fine-Tuning☆95Updated 2 months ago
- ☆196Updated 2 months ago
- ☆53Updated 10 months ago
- Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)☆30Updated 2 months ago