ckkissane / crosscoder-model-diff-replicationLinks
Open source replication of Anthropic's Crosscoders for Model Diffing
☆59Updated 11 months ago
Alternatives and similar repositories for crosscoder-model-diff-replication
Users that are interested in crosscoder-model-diff-replication are comparing it to the libraries listed below
Sorting:
- ☆54Updated 11 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- ☆190Updated last week
- ☆179Updated 11 months ago
- ☆131Updated this week
- ☆126Updated last year
- ☆36Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- ☆92Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 3 months ago
- ☆73Updated last week
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆26Updated 8 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆247Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆82Updated 10 months ago
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- ☆128Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 11 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆31Updated last month
- ☆107Updated 8 months ago
- Using sparse coding to find distributed representations used by neural networks.☆279Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆157Updated this week
- 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
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆28Updated last year