AutoAdminsteredAntidotes: Circuit detection in a poisoned model for MNIST classification

Kola Ayonrinde, Denizhan “Dennis” Akar, Kitti Kovács, Adam Newgas, David Quarel

AAA

Download instead.

Hackathon

Sunday, April 16, 2023

Hackathon

Jam site

Join the interpretability hackathon 2.0 online or from anywhere!

Global

Jam site

You have successfully rated this project!

Oops! Something went wrong while submitting the form.

You have successfully submitted your feedback. It should show up on this page.

Oops! Something went wrong while submitting the form.

Test

Test review

Dropout Incentivizes Privileged Bases

A test author

This is test feedback

[Example submission] OthelloScope

This project received

stars from a user

Fuzzing Large Language Models

This project received

stars from a user

Dropout Incentivizes Privileged Bases

This project received

stars from a user

[Example submission] OthelloScope