π Overcomplete is a Vision-based SAE Toolbox
β150Dec 4, 2025Updated 8 months ago
Alternatives and similar repositories for overcomplete
Users that are interested in overcomplete are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β76Jul 20, 2023Updated 3 years ago
- Code base for Universal Sparse Autoencoders (USAEs)β21Sep 7, 2025Updated 11 months ago
- πͺ Interpreto is an interpretability toolbox for LLMsβ198Updated this week
- β15Jan 2, 2023Updated 3 years ago
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ67Updated this week
- Managed hosting for WordPress and PHP on Cloudways β’ AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- β20May 1, 2025Updated last year
- LENS Projectβ53Feb 22, 2024Updated 2 years ago
- β40Sep 15, 2025Updated 11 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).β386Jul 23, 2025Updated last year
- [NeurIPS 2025] Interpreting vision transformers via residual replacement modelβ22Nov 3, 2025Updated 9 months ago
- Official code for FaCT: Faithful Concept Traces for Explaining Neural Network Decisions. NeurIPS 2025β20Mar 6, 2026Updated 5 months ago
- New implementations of old orthogonal layers unlock large scale training.β33Sep 19, 2025Updated 11 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 4 years ago
- β183May 1, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β44Mar 23, 2026Updated 5 months ago
- Unified access to Large Language Model modules using NNsightβ119Updated this week
- Training Sparse Autoencoders on Language Modelsβ1,514Aug 10, 2026Updated 2 weeks ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)β15Feb 24, 2026Updated 6 months ago
- Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorchβ11Aug 7, 2024Updated 2 years ago
- Visual Concept Connectomeβ15Jun 23, 2024Updated 2 years ago
- β428Aug 21, 2025Updated last year
- Temporal Neural Networksβ30Mar 2, 2026Updated 5 months ago
- Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"β33Apr 22, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean β’ AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explβ¦β12Jul 14, 2026Updated last month
- π Aligning Human & Machine Vision using explainabilityβ55Jul 14, 2023Updated 3 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.β1,080Updated this week
- β25Mar 30, 2026Updated 5 months ago
- Code for "Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models"β18Feb 16, 2026Updated 6 months ago
- Engine for collecting, uploading, and downloading model activationsβ31Apr 2, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).β272Feb 27, 2026Updated 6 months ago
- FastClassification is a tensorflow toolbox for class classification. It provides a training module with various backbones and training trβ¦β15Jun 26, 2021Updated 5 years ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)β67Jul 24, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive β’ AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β20May 29, 2024Updated 2 years ago
- β19Mar 5, 2024Updated 2 years ago
- π Puncc is a python library for predictive uncertainty quantification using conformal prediction.β403Updated this week
- β25Mar 17, 2021Updated 5 years ago
- Code for "Don't trust your eyes: on the (un)reliability of feature visualizations" (ICML 2024)β33Nov 15, 2023Updated 2 years ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ44Apr 17, 2024Updated 2 years ago
- [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilitβ¦β33Feb 5, 2026Updated 6 months ago