KempnerInstitute / overcompleteLinks
π Overcomplete is a Vision-based SAE Toolbox
β76Updated 3 weeks ago
Alternatives and similar repositories for overcomplete
Users that are interested in overcomplete are comparing it to the libraries listed below
Sorting:
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β66Updated 2 years ago
- LENS Projectβ48Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ32Updated 2 years ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β65Updated 2 years ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"β53Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaineβ¦β37Updated 2 years ago
- A toolkit for quantitative evaluation of data attribution methods.β53Updated last month
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformersβ41Updated 6 months ago
- β27Updated 2 years ago
- Codebase for Mechanistic Mode Connectivityβ15Updated 2 years ago
- β21Updated 9 months ago
- β14Updated 3 months ago
- Recycling diverse modelsβ45Updated 2 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabsβ36Updated 2 years ago
- Universal Neurons in GPT2 Language Modelsβ30Updated last year
- Personal implementation of ASIF by Antonio Norelliβ25Updated last year
- Sparse and discrete interpretability tool for neural networksβ63Updated last year
- [NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models".β43Updated 9 months ago
- Attribution-based Parameter Decompositionβ28Updated 2 months ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β19Updated last year
- β103Updated 6 months ago
- β46Updated 2 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"β97Updated 2 years ago
- Training and evaluating NBM and SPAM for interpretable machine learning.β78Updated 2 years ago
- Uncertainty-aware representation learning (URL) benchmarkβ105Updated 5 months ago
- π Aligning Human & Machine Vision using explainabilityβ52Updated 2 years ago
- Sparse Autoencoder Training Libraryβ54Updated 3 months ago
- ModelDiff: A Framework for Comparing Learning Algorithmsβ59Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paperβ59Updated last year
- β60Updated 3 years ago