dynamical-inference / patchsaeLinks
Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
☆20Updated 3 months ago
Alternatives and similar repositories for patchsae
Users that are interested in patchsae are comparing it to the libraries listed below
Sorting:
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆104Updated 2 years ago
- Sparse autoencoders for vision☆40Updated this week
- What do we learn from inverting CLIP models?☆55Updated last year
- ☆21Updated 7 months ago
- [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…☆130Updated 3 months ago
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆31Updated last year
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆49Updated 10 months ago
- Official repo for Detecting, Explaining, and Mitigating Memorization in Diffusion Models (ICLR 2024)☆76Updated last year
- ☆21Updated 5 months ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆15Updated 8 months ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆142Updated 3 months ago
- ☆14Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 10 months ago
- ☆68Updated 10 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆67Updated 6 months ago
- [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilit…☆22Updated 3 weeks ago
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆55Updated last year
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆28Updated last year
- ☆73Updated 3 years ago
- ☆46Updated last year
- LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters☆35Updated last month
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆40Updated 9 months ago
- Erasing conceptual knowledge from language models through low-rank fine-tuning☆19Updated 5 months ago
- A fast, effective data attribution method for neural networks in PyTorch☆217Updated 9 months ago
- ☆24Updated last year
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆77Updated 2 years ago
- ☆15Updated 4 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆47Updated 10 months ago
- Model Merging with SVD to Tie the KnOTS [ICLR 2025]☆65Updated 5 months ago
- [CVPR 2024] Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation☆46Updated last year