English
Related papers

Related papers: Concept Steerers: Leveraging K-Sparse Autoencoders…

200 papers

Sparse Autoencoders (SAEs) are widely used to interpret neural networks by identifying meaningful concepts from their representations. However, do SAEs truly uncover all concepts a model relies on, or are they inherently biased toward…

Machine Learning · Computer Science 2025-12-03 Sai Sumedh R. Hindupur , Ekdeep Singh Lubana , Thomas Fel , Demba Ba

To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier…

Machine Learning · Computer Science 2024-11-22 Sviatoslav Chalnev , Matthew Siu , Arthur Conmy

Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Chi-Pin Huang , Kai-Po Chang , Chung-Ting Tsai , Yung-Hsuan Lai , Fu-En Yang , Yu-Chiang Frank Wang

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Ouxiang Li , Yuan Wang , Xinting Hu , Houcheng Jiang , Yanbin Hao , Fuli Feng

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based…

Computation and Language · Computer Science 2025-03-05 Zhengxuan Wu , Aryaman Arora , Atticus Geiger , Zheng Wang , Jing Huang , Dan Jurafsky , Christopher D. Manning , Christopher Potts

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on…

Computation and Language · Computer Science 2026-05-25 Yusser Al Ghussin , Daniil Gurgurov , Tanja Baeumel , Josef van Genabith , Patrick Schramowski , Simon Ostermann

Diffusion-based models have gained significant popularity for text-to-image generation due to their exceptional image-generation capabilities. A risk with these models is the potential generation of inappropriate content, such as biased or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Hang Li , Chengzhi Shen , Philip Torr , Volker Tresp , Jindong Gu

Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Gerasimos Chatzoudis , Zhuowei Li , Gemma E. Moran , Hao Wang , Dimitris N. Metaxas

The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Mengyao Lyu , Yuhong Yang , Haiwen Hong , Hui Chen , Xuan Jin , Yuan He , Hui Xue , Jungong Han , Guiguang Ding

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han

Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Viet Nguyen , Vishal M. Patel

We present a method to create interpretable concept sliders that enable precise control over attributes in image generations from diffusion models. Our approach identifies a low-rank parameter direction corresponding to one concept while…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Rohit Gandikota , Joanna Materzynska , Tingrui Zhou , Antonio Torralba , David Bau

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Machine Learning · Computer Science 2025-02-25 Subhash Kantamneni , Joshua Engels , Senthooran Rajamanoharan , Max Tegmark , Neel Nanda

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives…

Machine Learning · Computer Science 2025-07-01 Kenny Peng , Rajiv Movva , Jon Kleinberg , Emma Pierson , Nikhil Garg

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Seunghoo Hong , Juhun Lee , Simon S. Woo

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Masane Fuchi , Tomohiro Takagi

Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where…

Graphics · Computer Science 2025-10-07 Ronen Kamenetsky , Sara Dorfman , Daniel Garibi , Roni Paiss , Or Patashnik , Daniel Cohen-Or