Transformers Explained Visually

70 points by aray07 2 hours ago on hackernews | 8 comments

tanseydavid | an hour ago

Nice work. I really appreciate this tool for enhancing my limited understanding the mechanism(s) behind attention and LLMs.

jwpapi | an hour ago

Damn that page took down my Chromebook, never happened before..
twice...
Text under the "Examples" section...

"Try examples while GPT-2 model is being downloaded (600MB)"

That's a hefty chunk of download and likely compute too.

utopcell | 57 minutes ago

Great site, intuitive description. I also found [1] very useful in the past.

[1] https://bbycroft.net/llm

This is not at all what I was hoping for. Expected a lot more Unicron.

andblac | 37 minutes ago

Nicely done. For me the most fascinating thing about attention heads is the place where Attention matrix is already computed and is getting multiplied by Value vector. It behaves exactly like pushing Value vector through Dense layer of ordinary network where Attention matrix forms weights of that layer. So attention head is trained to construct this small single layer network dynamically during inference from Key and Query. And that's the point. That's rarely underlined in explanations of LLMs architecture and for me it's quite amazing that it works so well. This mechanism easy to observe in this particular visualization if you click through it.

E-Reverance | 25 minutes ago

I get that this is for explaining GPT-2, but I really hope laymen don't use it as an example of how modern models work (ex. absolute positional encoding is no longer used)

edit: I know that it mentions its not modern, but these kinds of details have major implications in terms of the representations a model can learn, which is in many ways the most important part!