Video yükleniyor...
Video Yüklenemedi
Benjamin Bycroft’s 3D interactive tool visualizes an LLM’s layers, weights and matrix operations. This is the best educational tool to understand how an LLM works i've seen. httpx://bbycroft.net/llm
30,150 görüntüleme • 3 ay önce •via X (Twitter)
14 Yorum

This is genuinely one of the best LLM explainers I've seen. The way it shows attention turning raw tokens into structured meaning through nothing but matrix multiplies and layer norms is hypnotic. Makes you realize we're just watching a giant optimized calculator hallucinate coherence in real time.

Learning

Nice song

what gets me is watching the residual stream branch at attention heads in real time. most diagrams flatten that into arrows. wish it showed KV cache behavior too, that's where half the inference cost hides

I think I will finally take some time to get over this. No more guessing.

This visualization is really incredible 😎💯

Bookmarked. The 3D attention head visualisation finally made transformers click for me visually.

No idea, but the way you slam it together, ok ☕️🥞🍊

matrix ops you can actually click through is the killer learning tool

This is incredible

Wow, awesome! 🙌🏻

So I have finally went through this and I have to say that despite the visualization is really nice I didn't learn much. This literally goes over the lowest level, but tells you nothing about 'WHY?'

Oh heck yeah! These demos are 🔥

Deep-dive content
