NHacker Next
- new
- past
- show
- ask
- show
- jobs
- submit
login
This is a really cool dive into the interpretability of intermediate-level neural network activations. I really like the way that they've identified a core debate in the ML conversation, and created a relatively simple test-space to better understand it and (hopefully) move the discussion forward.
Very nice. Was a bit confused by the jump to splines and fitting splines to butterflies, more explanation would be appreciated
They write about neurons having “meaning” without a strict definition. What’s the quantitative meaning of meaning?
They fulfill a task, if you want the short answer.
No idea how to define 'task' here
This isn't immediately clear on whether it's discussing biological neurons or artificial neurons. I suppose it's the latter.
All the authors are part of OpenAI, and the very first sentence talks about computer vision and a parallel with real neurons. So "This isn't immediately clear" should be read as "I only read the title and didn't even try to understand what the article is about".
Rendered at 00:51:40 GMT+0000 (Coordinated Universal Time) with Vercel.