dribnet

@drib.net

creations with code and networks

what concepts does a model learn when learning to be a good chatbot? recent results in mechanistic interpretability surprisingly now allow these to be isolated and examined. here's one I found surprising: a peaked interest in social media and digital culture

Bild

Since submitting the @unireps.bsky.social paper I've continued to experiment with my pipeline, and have a version that is simplified visually and works much better as a physical print. For this I look at only the 100 maximum activations and places the strongest closer to the center.

Bild

I'll be at @unireps.bsky.social this Saturday presenting a new experimental pipeline to visually explore structured neural network representations. The core idea is to take thousands of prompts that activate a concept, and then cluster and draw them using MultiDiffusion. 🧵👇

Bild

i've been following the steady advance of mechanistic interpretability and what it can teach us about machine representations. this has led to some new creative directions which i hope to share with you soon. ✌️

Bild

what's this account for anyway? does it even handle giant files? maybe this will be where i hurl random things into the void...

Bild

Blowing Nose (2023). Screen print created by neural networks trained to classify dynamic scenes from videos of human behavior. The repeating patterns can be unrolled into a looping video and recognized by computer vision systems. Using Kinetics video dataset of human actions category "blowing nose".

Bild