ApolloResearch / apdLinks
Attribution-based Parameter Decomposition
☆28Updated last month
Alternatives and similar repositories for apd
Users that are interested in apd are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆109Updated 3 weeks ago
- ☆64Updated this week
- ☆51Updated 8 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- ☆32Updated last year
- A library for efficient patching and automatic circuit discovery.☆73Updated 2 weeks ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 6 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Engine for collecting, uploading, and downloading model activations☆20Updated 4 months ago
- ☆124Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆183Updated 3 weeks ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆20Updated 2 weeks ago
- ☆234Updated 10 months ago
- Unified access to Large Language Model modules using NNsight☆37Updated 2 weeks ago
- ☆15Updated 3 months ago
- 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
- ☆103Updated 5 months ago
- ☆81Updated 5 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- ☆28Updated last year
- Modified to support crosscoder training.☆21Updated last week
- Applying SAEs for fine-grained control☆23Updated 7 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year