Browse Games
Game Jams
Upload Game
Developer Logs
Community
Log in
Register
Indie game store
Free games
Fun games
Horror games
Game development
Assets
Comics
Sales
Bundles
Jobs
Tags
The Interpretability Hackathon
Hosted by
Zaki
,
Apart Research
,
Esben Kran
,
StefanHex
,
calcan
,
Neel Nanda
路
#alignmentjam
9
Entries
32
Ratings
Overview
Submissions
Results
Screenshots
Submission feed
Filter Submissions
Filter Results
Dropout incentivises privileged bases
EdoardoPona
Solving the CNN Mech Int Challenge
StefanHex
Detecting Phase Transitions
jhoogland
Algorithmic Explanation: A method for measuring interpretations of neural networks
clementneo
Improving TransformerLens Head Detector
MatthewBaggins
Orthello Mechint playground
victorlf4
AutoAdminsteredAntidotes: Circuit detection in a poisoned model for MNIST classification
kkittif
OthelloScope: Visualization of Game-Playing Transformer MLPs
Apart Research
Exploring OthelloGPT
Yeutong
