Show HN: LLM Attention Visualization (ishamf.dev)

156 pointsby ifz17 hours ago24 comments

mncharity 9 hours ago

UX report. I wished to examine attention state step by step, but I found the animation moved along too fast for that. So I tried pausing...

On Chromium/linux, pressing pause doesn't pause, instead resetting the animation to it's pre-play state - the current attention highlighting disappears. Pressing play again, restarts at the beginning. Having a commonplace "pause pauses, and play resumes" UI, could allow more time to look over state. A youtube-like slow playback 0.25? option might similarly help. Or perhaps even better, buttons for single stepping. Tnx for your work.

MCP123 12 hours ago

This is great, thank you. I have to teach this stuff on Friday so perfect timing. It's hard to explain the attention mechanism in a way that becomes intuitive because the weighting scheme does not help much with the intuition. Having a visualization like this helps a lot. Don't move that page please since I'll link to it!

fuddle 15 hours ago

This is great, I've read multiple books and watched videos about the attention mechanism. Now that I understand it, this is the clearest example I've seen on how attention works.

lhk931122 8 hours ago

Is the attention explanation of why the model tells like this? I've seen that there are many discussions about this. (Image attention visualizations were not that good I think)

scottcodie 8 hours ago

You can also mine attention from image models, it's a lot of fun and very interesting.

talhaanwar 4 hours ago

thanks for making it simple and visualizable

sva_ 16 hours ago

I highly question this simplistic idea of high vector magnitude = high influence.

ifz 16 hours ago

I don't disagree with that. I did add an entire caveat paragraph there.

To me, it's more of a neat visualization, not something that can be used to interpret LLM behavior. Even with a lot of simplification, it can show some interesting patterns.

smallmancontrov 16 hours ago

You get what you pay for. If you want to think harder and get more, https://transformer-circuits.pub/2025/attention-qk/index.htm...

apnabhidu47 15 hours ago

Same I dont get it just, could you clarify it

wopak 15 hours ago

neat, combining info from two phrases is hard to see without such a tool.

are you worried later-layer attention gets drowned out by earlier layers just because there are more of them contributing to the sum?

ifz 15 hours ago

Hmm, I might try to add some controls to limit which layers get summed up. It might be able to reveal more patterns.

Right now only simple correlations are visible.

asd000hh 6 hours ago

How it works?

itsnasme 15 hours ago

I like the visualisation. Pretty cool

stared 15 hours ago

I am curious what's the actual formula.

I mean, there so many headers and layers, it is tricky to make a choice that will resonate with our intuition . Is it some weighted average? Or maybe ablation test?

ifz 15 hours ago

It's really simple, basically just the magnitude of the value vector, weighted by QK dot product, summed across all attention heads and layers.

When I started, I expected I'd have to experiment a lot to find something comprehensible. But this simple computation can already show some patterns.

stared 14 hours ago

Nice! Sometimes the simplest approaches work the best.

visarga 14 hours ago

If you want quick access look at google images for "transformer attention formula" there are some interesting depictions

ex-aws-dude 14 hours ago

I don't know much about LLMs but does that mean you have N^2 computation with the context size since every token needs to track how it relates to every other token?

acedTrex 14 hours ago

For full self attention yes

TomatoCo 13 hours ago

Yes, except no with the KV cache. Because tokens aren't modified by future tokens you can cache the meaning of previous tokens. This makes the total effort linear over the entire context (or constant per forward pass).

ex-aws-dude 13 hours ago

I see and is there only 1 layer of relations?

Or does it accumulate the relations like A relates to B, so also add in B's relations

libraryofbabel 12 hours ago

> This makes the total effort linear over the entire context (or constant per forward pass).

This is incorrect. The compute required per forward pass to generate each additional token during decode will scales as O(N), even with a KV cache (without a KV cache, it would scale as O(N^2)). Over generating N tokens, it's O(N^2) with the cache (and O(N^3) without).

It's O(N) for a forward pass because that new token still has to "attend to" to each previous token. That requires N dot products: between the cached key vectors and the new query vector for the new position. You also have N reads from memory (K and V) which is probably gonna be your actual bottleneck. (Decode is memory-bound.)

This is why you should avoid long contexts, if you can, even with a warm cache. You will get charged more, in "cache read" tokens.

fermlon30000 11 hours ago

INSANE