Joseph, Sonia

1. Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
   2025/04/28 by Joseph, Sonia, Suresh, Praneet, Hufe, Lorenz +7 · 10 citations
   #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
2. Steering CLIP's vision transformer with sparse autoencoders
   2025/04/11 by Joseph, Sonia, Suresh, Praneet, Goldfarb, Ethan +6 · 7 citations
   #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
3. How Visual Representations Map to Language Feature Space in Multimodal LLMs
   2025/06/13 by Venhoff, Constantin, Khakzar, Ashkan, Joseph, Sonia +2 · 7 citations
   #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
4. Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
   2025/10/08 by Fel, Thomas, Wang, Binxu, Lepori, Michael A. +8 · 1 citation
   #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
5. From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
   2025/09/08 by Praneet Suresh, Suresh, Praneet, Jack Stanley +7 · 1 voice · 2 citations
   Psychology · #Paranormal Experiences and Beliefs #Psychedelics and Drug Studies #cs.AI #cs.LG