ApolloResearch / e2e_sae
Sparse Autoencoder Training Library
☆42Updated 4 months ago
Alternatives and similar repositories for e2e_sae:
Users that are interested in e2e_sae are comparing it to the libraries listed below
- ☆60Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆56Updated 3 weeks ago
- ☆32Updated 2 weeks ago
- ☆62Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆44Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆29Updated 9 months ago
- ☆120Updated last year
- ☆18Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 9 months ago
- ☆61Updated 2 years ago
- ☆159Updated this week
- Universal Neurons in GPT2 Language Models☆27Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆70Updated 3 months ago
- Sparse probing paper full code.☆55Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆40Updated 5 months ago
- ☆26Updated 11 months ago
- ☆29Updated 10 months ago
- ☆112Updated 7 months ago
- ☆41Updated last month
- ☆21Updated 2 weeks ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated 2 weeks ago
- ☆149Updated this week
- ☆80Updated 7 months ago
- ☆210Updated 5 months ago
- ☆31Updated 3 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated last month
- Algebraic value editing in pretrained language models☆63Updated last year
- ☆21Updated last month
- ☆88Updated last month