JoshEngels / SAE-Dark-MatterLinks
Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"
☆22Updated 3 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:
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year
- Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"☆20Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆89Updated last week
- Sparse Autoencoder Training Library☆52Updated last month
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated 11 months ago
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆23Updated 6 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆78Updated 7 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- A mechanistic approach for understanding and detecting factual errors of large language models.☆45Updated 11 months ago
- ☆83Updated 9 months ago
- Measuring the situational awareness of language models☆35Updated last year
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆43Updated 6 months ago
- Attribution-based Parameter Decomposition☆23Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆181Updated this week
- ☆34Updated 2 weeks ago
- ☆28Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆96Updated 3 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆87Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆107Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆103Updated 3 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- Universal Neurons in GPT2 Language Models☆29Updated last year
- ☆29Updated 10 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆26Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 7 months ago
- ☆29Updated last year