Skip to main content
itch.io
Browse Games
Game Jams
Upload Game
Summer Sale 2026
Developer Logs
Community
Log in
Register
The Power of Pride Bundle 2026 — $10 PWYC Edition
On Sale:
Games
Assets
Tools
Tabletop
Comics
Indie game store
Free games
Fun games
Horror games
Game development
Assets
Comics
Sales
Bundles
Jobs
Tags
Game Engines
The Interpretability Hackathon
Hosted by
Zaki
,
Apart Research
,
Esben Kran
,
StefanHex
,
calcan
,
Neel Nanda
·
#alignmentjam
9
Entries
32
Ratings
Overview
Submissions
Results
Screenshots
Submission feed
Filter Submissions
Filter Results
OthelloScope: Visualization of Game-Playing Transformer MLPs
Apart Research
Dropout incentivises privileged bases
EdoardoPona
Solving the CNN Mech Int Challenge
StefanHex
Improving TransformerLens Head Detector
MatthewBaggins
Algorithmic Explanation: A method for measuring interpretations of neural networks
clementneo
Detecting Phase Transitions
jhoogland
Exploring OthelloGPT
Yeutong
Orthello Mechint playground
victorlf4
AutoAdminsteredAntidotes: Circuit detection in a poisoned model for MNIST classification
kkittif
