I'm not great with this sort of optimization of this, but I definitely followed Neil Nand as we're quite a bit in what I understand from his YouTube tutorials. There's a divergence between the representation of the attention mechanism that is most compute efficient and therefore gets used in code from a more, you know, purely analytical representation that's like easier to interpret. Do I have that right? Or am I going off track somewhere? Sorry, what do you mean by low representation here? So you had set a second ago that the sort of multiple matrix operations that constitute the transformer mechanism in analytical terms are not really separable, but they are in practice,. As I understand it, they are

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode