ApolloResearch / e2e_saeLinks
Sparse Autoencoder Training Library
☆54Updated 5 months ago
Alternatives and similar repositories for e2e_sae
Users that are interested in e2e_sae are comparing it to the libraries listed below
Sorting:
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆34Updated last year
- ☆71Updated last month
- ☆23Updated 8 months ago
- ☆127Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Updated 2 weeks ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- ☆106Updated 7 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- ☆54Updated 10 months ago
- ☆125Updated 2 weeks ago
- ☆91Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- ☆187Updated 2 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆123Updated last year
- ☆23Updated 10 months ago
- ☆23Updated last year
- Engine for collecting, uploading, and downloading model activations☆23Updated 6 months ago
- ☆242Updated last year
- 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 to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- ☆29Updated last year