callummcdougall / sae-exercises-matsLinks
☆22Updated last year
Alternatives and similar repositories for sae-exercises-mats
Users that are interested in sae-exercises-mats are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder Training Library☆52Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- ☆23Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- Universal Neurons in GPT2 Language Models☆29Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆95Updated 2 weeks ago
- A small package implementing some useful wrapping around nnsight☆13Updated this week
- ☆44Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- ☆31Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Measuring the situational awareness of language models☆35Updated last year
- ☆85Updated 10 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆109Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆43Updated 6 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated last year
- ☆14Updated last year
- ☆10Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- Attribution-based Parameter Decomposition☆25Updated 2 weeks ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆37Updated 7 months ago
- ☆28Updated last year
- ☆15Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 5 months ago
- ☆57Updated 2 weeks ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆14Updated 8 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 5 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year