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.
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.
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?
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.
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?
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.
I like the visualisation. Pretty cool
I highly question this simplistic idea of high vector magnitude = high influence.
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.
You get what you pay for. If you want to think harder and get more, https://transformer-circuits.pub/2025/attention-qk/index.htm...
Same I dont get it just, could you clarify it
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?
If you want quick access look at google images for "transformer attention formula" there are some interesting depictions
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.
Nice! Sometimes the simplest approaches work the best.