Using 'im feeling lucky' from the neuron viewer is a really cool way to explore ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		bottlepalm on May 9, 2023 \| parent \| context \| favorite \| on: Language models can explain neurons in language mo... Using 'im feeling lucky' from the neuron viewer is a really cool way to explore different neurons. And then being able to navigate up and down through the net to related neurons.

eternalban on May 9, 2023 [–]

Fun to look at activations and then search for the source on the net.

"Suddenly, DM-sliding seems positively whimsical"

https://openaipublic.blob.core.windows.net/neuron-explainer/...

https://www.thecut.com/2016/01/19th-century-men-were-awful-a...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact