JoshEngels / SAE-Dark-Matter
Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"
☆14Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for SAE-Dark-Matter
- Sparse and discrete interpretability tool for neural networks☆54Updated 9 months ago
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆38Updated last year
- ☆70Updated 3 months ago
- A mechanistic approach for understanding and detecting factual errors of large language models.☆39Updated 4 months ago
- ☆24Updated last year
- ☆24Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- ☆105Updated this week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆60Updated last month
- ☆18Updated last month
- ☆19Updated 3 months ago
- ☆43Updated 4 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- ☆13Updated 2 months ago
- Evaluation of neuro-symbolic engines☆33Updated 3 months ago
- Measuring the situational awareness of language models☆33Updated 9 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆83Updated 7 months ago
- ☆68Updated 3 months ago
- Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data☆30Updated 2 months ago
- ☆102Updated last month
- Repository for the paper Stream of Search: Learning to Search in Language☆84Updated 3 months ago
- Universal Neurons in GPT2 Language Models☆26Updated 5 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆61Updated 4 months ago
- Tasks for describing differences between text distributions.☆16Updated 3 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆55Updated last year
- Codebase for Inference-Time Policy Adapters☆21Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆118Updated last month
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆25Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆74Updated this week
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆48Updated 7 months ago