π Overcomplete is a Vision-based SAE Toolbox
β123Dec 4, 2025Updated 2 months 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)β71Jul 20, 2023Updated 2 years ago
- New implementations of old orthogonal layers unlock large scale training.β29Sep 19, 2025Updated 5 months ago
- πͺ Interpreto is an interpretability toolbox for LLMsβ144Updated this week
- β39Sep 15, 2025Updated 5 months ago
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ66Updated this week
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)β16Updated this week
- β16May 1, 2025Updated 10 months ago
- π Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)β33Jul 18, 2022Updated 3 years ago
- β17Aug 30, 2025Updated 6 months ago
- Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explβ¦β12Apr 4, 2025Updated 10 months ago
- Official code base for NeurIPS 2021 SVRHM Workshop poster "On the use of Cortical Magnification and Saccades as Biological Proxies for Daβ¦β13Jun 28, 2023Updated 2 years ago
- Temporal Neural Networksβ28Updated this week
- π Aligning Human & Machine Vision using explainabilityβ53Jul 14, 2023Updated 2 years ago
- β13Oct 5, 2025Updated 4 months ago
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ102Mar 14, 2025Updated 11 months ago
- πͺPISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Modelsβ12May 30, 2025Updated 9 months ago
- Generic Engine for Multi-disciplinary Scenarios, Exploration and Optimization. This is a MIRROR of our gitlab repository, the developmentβ¦β31Updated this week
- Reference implementation of Thin and Deep Gaussian Processes (NeurIPS 2023)β14Nov 25, 2024Updated last year
- Implementation of the ICLR 2022 paper "Phase Collapse in Neural Networks."β10Mar 21, 2022Updated 3 years ago
- β13Jul 26, 2023Updated 2 years ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformersβ43Feb 12, 2025Updated last year
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/β26Mar 10, 2025Updated 11 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).β340Jul 23, 2025Updated 7 months ago
- Trains Sparse Autoencoders based on outputs from language modelsβ11Oct 7, 2024Updated last year
- This repository represents a basic implementation of the paper "Riemannian Geometry of Deep Generative Models", along with the results onβ¦β12Oct 23, 2019Updated 6 years ago
- β16Apr 7, 2025Updated 10 months ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"β14Nov 22, 2024Updated last year
- β24Oct 3, 2025Updated 4 months ago
- This repository includes the code to download the curated HuggingFace papers into a single markdown formatted fileβ16Jul 26, 2024Updated last year
- FastClassification is a tensorflow toolbox for class classification. It provides a training module with various backbones and training trβ¦β15Jun 26, 2021Updated 4 years ago
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β39Feb 2, 2026Updated 3 weeks ago
- Attribution-based Parameter Decompositionβ34Jun 11, 2025Updated 8 months ago
- β19Sep 16, 2025Updated 5 months ago
- A generalized model fitting pipeline that houses models, trainers, and datasets in datajoint and returns as well as stores trained modelsβ¦β19Apr 9, 2024Updated last year
- hdnet - Hopfield denoising networkβ14Oct 6, 2022Updated 3 years ago
- Pokedex for LLMsβ14Apr 14, 2025Updated 10 months ago
- Implementing Visual Saliency Modelsβ13Jan 10, 2018Updated 8 years ago
- Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.β60Feb 17, 2026Updated last week
- CS194-196 Course Projectβ14Feb 20, 2025Updated last year