Jonathan Jacobi (@j0nathanj) 's Twitter Profile
Jonathan Jacobi

@j0nathanj

Mainly doing AI and hacking things. Co-Founder @pb_ctf

ID: 895363940162707456

linkhttp://j0nathanj.github.io calendar_today09-08-2017 19:19:33

1,1K Tweet

3,3K Followers

935 Following

Jonathan Jacobi (@j0nathanj) 's Twitter Profile Photo

🚀 We're excited to share our brand-new paper! Introducing “Superscopes”—an effective new method to uncover hidden meanings from an LLM's thinking process! Superscopes amplifies subtle internal features in LLMs, revealing weak yet meaningful features that previous methods

🚀 We're excited to share our brand-new paper!

Introducing “Superscopes”—an effective new method to uncover hidden meanings from an LLM's thinking process!

Superscopes amplifies subtle internal features in LLMs, revealing weak yet meaningful features that previous methods