Federico Torrielli

EvilScript

·

https://federicotorrielli.github.io

AI & ML interests

AI Safety & Mechanistic interpretability

Recent Activity

authored a paper 3 days ago

Selecting The Most Informative Tokens in Natural Language Autoencoders

submitted a paper 4 days ago

Selecting The Most Informative Tokens in Natural Language Autoencoders

upvoted a paper 4 days ago

Selecting The Most Informative Tokens in Natural Language Autoencoders

View all activity

Organizations

EvilScript 's papers 6

arxiv:2609.37040

arxiv:2606.10747

arxiv:2606.09697

arxiv:2605.31170

arxiv:2605.26045

arxiv:2605.07462