Alexander Gietelink Oldenziel
- Transformers represent belief state geometry in their residual stream
2024/05/24 by Adam S. Shai, Shai, Adam S., Sarah Marzen +7 · 16 citations
Computer Science · #Computation and Language (cs.CL) #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms