Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
☆34Apr 22, 2026Updated 6 months ago
Alternatives and similar repositories for patchsae
Users that are interested in patchsae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of paper: Characterizing Dataset Bias via Disentangled Visual Concepts☆14Oct 30, 2025Updated last year
- Official implementation of CytoSAE: Interpretable Cell Embeddings for Hematology☆27Jul 17, 2025Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆62Nov 3, 2024Updated 2 years ago
- Code base for Universal Sparse Autoencoders (USAEs)☆23Sep 7, 2025Updated last year
- Official implementation for "Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning"☆12Jun 20, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- The code for the paper "Pre-trained Vision-Language Models Learn Discoverable Concepts"☆21Jun 5, 2024Updated 2 years ago
- Sparse autoencoders for vision☆69Sep 25, 2026Updated last month
- ☆13Jun 11, 2025Updated last year
- ☆12Oct 12, 2024Updated 2 years ago
- ☆186May 1, 2026Updated 6 months ago
- Sparse Linear Concept Embeddings☆137Mar 27, 2025Updated last year
- Code for the ACL 2023 paper Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Sc…☆12May 19, 2023Updated 3 years ago
- ☆75Jan 17, 2025Updated last year
- ☆13Jan 31, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆20Jun 20, 2025Updated last year
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- [NeurIPS 2025] This is the official repository for VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Se…☆15Oct 3, 2026Updated last month
- [ICML 2025] Unlearning in Diffusion Models using Sparse Autoencoders☆66Oct 16, 2025Updated last year
- Repository for the paper "Interpreting Temporal Graph Neural Networks with Koopman Theory"☆12Apr 7, 2026Updated 7 months ago
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆36Jun 5, 2025Updated last year
- ☆36Feb 5, 2024Updated 2 years ago
- [ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment☆18Jun 5, 2025Updated last year
- Vision-Language Fine-tuning with Pathology Reports | Conch-Z [Neurips 2026 Spotlight]☆23Oct 14, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ECCV24] Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning☆10Dec 9, 2024Updated last year
- ☆10Jul 5, 2024Updated 2 years ago
- [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilit…☆36Feb 5, 2026Updated 9 months ago
- Official code for "Algorithmic Capabilities of Random Transformers" (NeurIPS 2024)☆16Sep 28, 2024Updated 2 years ago
- 🥚 EnerGy Guided Diffusion for optimizing neurally exciting images☆10Dec 20, 2023Updated 2 years ago
- Integrating Clinical Knowledge into Concept Bottleneck Models (MICCAI2024)☆15Sep 12, 2024Updated 2 years ago
- Code for Learned Thresholds Token Merging and Pruning for Vision Transformers (LTMP). A technique to reduce the size of Vision Transforme…☆17Nov 24, 2024Updated last year
- This is the official implementation of the Concept Discovery Models paper.☆15Aug 27, 2023Updated 3 years ago
- ☆25Apr 23, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆24Mar 4, 2022Updated 4 years ago
- [COLM 2026] Resa: Transparent Reasoning Models via SAEs☆49Sep 23, 2025Updated last year
- ☆20Feb 6, 2026Updated 9 months ago
- [CVPR'25] Attention IoU: Examining Biases in CelebA using Attention Maps☆13Mar 26, 2025Updated last year
- ☆11May 6, 2024Updated 2 years ago
- ☆14Apr 10, 2025Updated last year
- Official Repository for Frame Representation Hypothesis paper☆10Oct 26, 2026Updated 3 weeks ago
Are these results useful?