Alternatives and similar repositories for patchsae

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

• samyadeepbasu / LocoGen
  Localization of Knowledge in Text-to-Image Models
  ☆11Updated last year
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆57Updated last year
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆107Updated 2 years ago
• OSU-NLP-Group / saev
  Sparse autoencoders for vision
  ☆52Updated this week
• sail-sg / D-TRAK
  Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
  ☆35Updated last year
• kingdy2002 / SPA
  ☆24Updated 11 months ago
• dtch1997 / steering-bench
  Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"
  ☆18Updated last year
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆41Updated last year
• chs20 / RobustVLM
  [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
  ☆149Updated 6 months ago
• neuroexplicit-saar / Discover-then-Name
  Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
  ☆52Updated last year
• OPTML-Group / Unlearn-Saliency
  [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…
  ☆141Updated 6 months ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆109Updated 2 weeks ago
• rohitgandikota / erasing-llm
  Erasing conceptual knowledge from language models through low-rank fine-tuning
  ☆19Updated 8 months ago
• clemneo / llava-interp
  ☆76Updated 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…
  ☆28Updated 4 months ago
• adamkarvonen / SAEBench
  ☆136Updated last month
• serre-lab / Horama
  ☆16Updated 7 months ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆78Updated last year
• 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…
  ☆10Updated 9 months ago
• YuxinWenRick / diffusion_memorization
  Official repo for Detecting, Explaining, and Mitigating Memorization in Diffusion Models (ICLR 2024)
  ☆77Updated last year
• cywinski / SAeUron
  [ICML 2025] Unlearning in Diffusion Models using Sparse Autoencoders
  ☆48Updated 2 months ago
• aypan17 / latentqa
  ☆23Updated last month
• KihoPark / linear_rep_geometry
  ☆112Updated 10 months 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
• dgcnz / FACT
  Code for [Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models.
  ☆12Updated last year
• harveyhuang18 / EMR_Merging
  [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging
  ☆74Updated 9 months ago
• ExplainableML / sae-for-vlm
  [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
  ☆52Updated 3 weeks ago
• thestephencasper / latent_adversarial_training
  ☆23Updated last year
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆327Updated 4 months ago
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆51Updated last year