Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

31 January 2025

Papers citing "Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations"

6 / 6 papers shown

Title
Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression Yiwei Xie Ping Liu Zheng Zhang 93 0 0 26 May 2025
Emergence and Evolution of Interpretable Concepts in Diffusion Models Berk Tinaz Zalan Fabian Mahdi Soltanolkotabi DiffM 50 0 0 21 Apr 2025
Understanding the Repeat Curse in Large Language Models from a Feature Perspective Junchi Yao Shu Yang Jianhua Xu Lijie Hu Mengdi Li Di Wang 89 1 0 19 Apr 2025
Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts Leyang Li Shilin Lu Yan Ren A. Kong DiffM 80 4 0 17 Apr 2025
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models Mateusz Pach Shyamgopal Karthik Quentin Bouniot Serge Belongie Zeynep Akata VLM 98 2 0 03 Apr 2025
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders Bartosz Cywiński Kamil Deja DiffM 103 8 0 29 Jan 2025