FlyingPumba / InterpBenchLinks
A benchmark for mechanistic discovery of circuits in Transformers
☆14Updated 5 months ago
Alternatives and similar repositories for InterpBench
Users that are interested in InterpBench are comparing it to the libraries listed below
Sorting:
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- ☆97Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 4 months ago
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆16Updated 6 months ago
- Sparse Autoencoder Training Library☆50Updated last month
- Attribution-based Parameter Decomposition☆23Updated this week
- ☆223Updated 8 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆16Updated 7 months ago
- ☆75Updated 3 months ago
- ☆43Updated 6 months ago
- ☆171Updated last month
- 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
- ☆12Updated last month
- ☆34Updated 2 weeks ago
- ☆120Updated 6 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 4 months ago
- ☆33Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated last week
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- ☆121Updated last year
- ☆19Updated last month
- ☆31Updated last year
- Sparse probing paper full code.☆56Updated last year