JasonGross / guarantees-based-mechanistic-interpretabilityLinks
☆14Updated 2 weeks ago
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:
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 4 months ago
- Harmonic Datasets☆40Updated 10 months ago
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- An environment for learning formal mathematical reasoning from scratch☆67Updated 9 months ago
- Learning Formal Mathematics from Intrinsic Motivation☆30Updated 2 months ago
- Tools for studying developmental interpretability in neural networks.☆91Updated 4 months ago
- Formalizing stochastic doubly-efficient debate☆105Updated 7 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- (Model-written) LLM evals library☆18Updated 5 months ago
- Attribution-based Parameter Decomposition☆23Updated this week
- ☆57Updated 2 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆31Updated last year
- Repository with sample code using Apollo's suggested engineering practices☆9Updated 5 months ago
- Sparse Autoencoder Training Library☆50Updated last month
- ☆120Updated 6 months ago
- Tutorial on neural theorem proving☆174Updated last year
- ☆50Updated last month
- ☆43Updated 6 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- ☆63Updated 2 years ago
- COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.☆62Updated 3 weeks ago
- https://albertqjiang.github.io/Portal-to-ISAbelle/☆56Updated last year
- ☆131Updated 2 months ago
- Applying SAEs for fine-grained control☆18Updated 5 months ago
- Python wrapper for lean-gym☆11Updated 2 years ago
- Redwood Research's transformer interpretability tools☆15Updated 3 years ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated 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 last year