Alternatives and similar repositories for patchsae

Users that are interested in patchsae are comparing it to the libraries listed below

• OSU-NLP-Group / saev
  Sparse autoencoders for vision
  ☆55Updated 3 weeks ago
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆108Updated 2 years ago
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆58Updated last year
• sail-sg / D-TRAK
  Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
  ☆37Updated 2 years ago
• kingdy2002 / SPA
  ☆24Updated last year
• dtch1997 / steering-bench
  Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"
  ☆19Updated last year
• nickjiang2378 / vlm-hallucinations
  [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"
  ☆96Updated 2 months ago
• clemneo / llava-interp
  ☆79Updated last year
• Trustworthy-ML-Lab / CB-LLMs
  [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilit…
  ☆29Updated 5 months ago
• samyadeepbasu / LocoGen
  Localization of Knowledge in Text-to-Image Models
  ☆12Updated last year
• neuroexplicit-saar / Discover-then-Name
  Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
  ☆55Updated last year
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆42Updated last week
• zhqwqwq / Learning-Parity-with-CoT
  [ICLR 2025] This repository contains the code to reproduce the results from our paper From Sparse Dependence to Sparse Attention: Unveili…
  ☆12Updated 10 months ago
• chs20 / fuselip
  FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens
  ☆17Updated 4 months ago
• chs20 / RobustVLM
  [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
  ☆152Updated 7 months ago
• Heidelberg-NLP / CC-SHAP-VLM
  Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Expl…
  ☆12Updated 9 months ago
• wrudman / NOTICE
  ☆13Updated 9 months ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆117Updated last month
• serre-lab / Horama
  ☆16Updated 9 months ago
• aypan17 / latentqa
  ☆27Updated 2 months ago
• BigML-CS-UCLA / SpuCo
  SpuCo is a Python package developed to further research to address spurious correlations.
  ☆25Updated last year
• ExplainableML / sae-for-vlm
  [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
  ☆60Updated 2 months ago
• YuxinWenRick / diffusion_memorization
  Official repo for Detecting, Explaining, and Mitigating Memorization in Diffusion Models (ICLR 2024)
  ☆77Updated last year
• Trustworthy-ML-Lab / CLIP-dissect
  [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs
  ☆59Updated 2 years ago
• maxdreyer / PURE
  Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…
  ☆19Updated last year
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆51Updated last month
• paulgavrikov / vlm_shapebias
  Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).
  ☆27Updated last year
• thaoshibe / awesome-personalized-lmms
  A curated list of Awesome Personalized Large Multimodal Models resources
  ☆52Updated 2 weeks ago
• EvolvingLMMs-Lab / multimodal-sae
  [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.
  ☆174Updated 4 months ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆79Updated last year