JasonGross / guarantees-based-mechanistic-interpretabilityLinks
☆14Updated 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:
- A small package implementing some useful wrapping around nnsight☆13Updated 3 weeks ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 5 months ago
- Tools for studying developmental interpretability in neural networks.☆94Updated 5 months ago
- (Model-written) LLM evals library☆18Updated 6 months ago
- ☆31Updated last year
- Attribution-based Parameter Decomposition☆25Updated 2 weeks ago
- Learning Formal Mathematics from Intrinsic Motivation☆30Updated 3 months ago
- Harmonic Datasets☆40Updated 11 months ago
- Redwood Research's transformer interpretability tools☆15Updated 3 years 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
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Python wrapper for lean-gym☆12Updated 2 years ago
- An environment for learning formal mathematical reasoning from scratch☆70Updated 10 months ago
- Applying SAEs for fine-grained control☆18Updated 6 months ago
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated last week
- A library for mechanistic anomaly detection☆22Updated 5 months ago
- ☆65Updated last month
- Formalizing stochastic doubly-efficient debate☆107Updated 8 months ago
- ☆134Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆57Updated 2 weeks ago
- ☆13Updated 2 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- https://albertqjiang.github.io/Portal-to-ISAbelle/☆56Updated last year
- ☆17Updated 6 months ago
- ☆44Updated 7 months ago
- ☆63Updated 2 years ago