JasonGross / guarantees-based-mechanistic-interpretabilityLinks
☆16Updated this week
Alternatives and similar repositories for guarantees-based-mechanistic-interpretability
Users that are interested in guarantees-based-mechanistic-interpretability are comparing it to the libraries listed below
Sorting:
- Harmonic Datasets☆45Updated last year
- LLMs + Lean, on your laptop or in the cloud☆175Updated 3 weeks ago
- ☆64Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 2 years ago
- ☆32Updated last year
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆202Updated this week
- Tools for studying developmental interpretability in neural networks.☆100Updated last month
- A library for mechanistic anomaly detection☆22Updated 7 months ago
- ☆136Updated 4 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- ☆63Updated 2 years ago
- Attribution-based Parameter Decomposition☆28Updated last month
- Neural theorem proving tutorial, version II☆38Updated last year
- ☆124Updated last year
- Formalizing stochastic doubly-efficient debate☆107Updated 10 months ago
- Open source interpretability artefacts for R1.☆157Updated 3 months ago
- ☆51Updated 8 months ago
- ☆157Updated 8 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
- Applying SAEs for fine-grained control☆23Updated 7 months ago
- The official implementation of "Self-play LLM Theorem Provers with Iterative Conjecturing and Proving"☆99Updated 4 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management☆69Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆120Updated 5 months ago
- Tutorial on neural theorem proving☆174Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- ☆104Updated 5 months ago