redwoodresearch / rust_circuit_publicLinks
☆63Updated 2 years ago
Alternatives and similar repositories for rust_circuit_public
Users that are interested in rust_circuit_public are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆94Updated 5 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
- ☆67Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆121Updated last year
- ☆227Updated 8 months ago
- Mechanistic Interpretability Visualizations using React☆257Updated 6 months ago
- ☆28Updated last year
- ☆120Updated 10 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated 2 weeks ago
- ☆44Updated 7 months ago
- (Model-written) LLM evals library☆18Updated 6 months ago
- ☆270Updated last year
- The Happy Faces Benchmark☆15Updated last year
- ☆19Updated 2 years ago
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- A benchmark for mechanistic discovery of circuits in Transformers☆14Updated 6 months ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ☆131Updated 7 months ago
- Attribution-based Parameter Decomposition☆25Updated 2 weeks ago
- Machine Learning for Alignment Bootcamp☆74Updated 3 years ago
- A library for mechanistic anomaly detection☆22Updated 5 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆65Updated last month
- ☆14Updated this week
- ☆173Updated 2 months ago
- 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