Hugging Face's logo
Jonas Loos's picture

Jonas Loos

JonasLoos
7 5 37
webbrain-one-309152's profile picture Koddenbrock's profile picture Juicstus's profile picture
·
https://jloos.de

AI & ML interests

Interpretability

Recent Activity

liked a dataset 8 days ago
thecraigd/emergent-misalignment-results
authored a paper 13 days ago
KV-Cache Patching: Tracing How and Where Fine-Tuned Behaviors Arise
updated a collection 13 days ago
KV-Cache Patching
View all activity

Organizations

0jl's profile picture Berlin Learning and Intelligent Systems Society's profile picture SD Research's profile picture research-tmp123's profile picture