FOR-sight-ai / interpretoLinks
πͺ Interpreto is an interpretability toolbox for LLMs
β35Updated last week
Alternatives and similar repositories for interpreto
Users that are interested in interpreto are comparing it to the libraries listed below
Sorting:
- π Overcomplete is a Vision-based SAE Toolboxβ90Updated 2 months ago
- Attribution-based Parameter Decompositionβ31Updated 4 months ago
- β52Updated last year
- Sparse Autoencoder Training Libraryβ55Updated 5 months ago
- Universal Neurons in GPT2 Language Modelsβ30Updated last year
- β19Updated 2 years ago
- Sparse and discrete interpretability tool for neural networksβ63Updated last year
- Tools for optimizing steering vectors in LLMs.β13Updated 6 months ago
- Interpreting how transformers simulate agents performing RL tasksβ88Updated last year
- Cost aware hyperparameter tuning algorithmβ171Updated last year
- Latent Program Network (from the "Searching Latent Program Spaces" paper)β98Updated last week
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β19Updated last year
- β35Updated last year
- A tiny easily hackable implementation of a feature dashboard.β15Updated 3 weeks ago
- β13Updated 7 months ago
- β81Updated 7 months ago
- Deep Networks Grok All the Time and Here is Whyβ37Updated last year
- nanoGPT-like codebase for LLM trainingβ108Updated 4 months ago
- β58Updated last year
- β120Updated 4 months ago
- Tools for studying developmental interpretability in neural networks.β105Updated 3 months ago
- Engine for collecting, uploading, and downloading model activationsβ24Updated 6 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabsβ35Updated 3 years ago
- Minimum Description Length probing for neural network representationsβ20Updated 8 months ago
- β23Updated 10 months ago
- TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.β21Updated 2 weeks ago
- A library for efficient patching and automatic circuit discovery.β77Updated 2 months ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]β22Updated this week
- A TinyStories LM with SAEs and transcodersβ13Updated 6 months ago
- β33Updated 10 months ago