Viewing profile — ifz

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.

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 …

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 wit…

I often need to convert times between time zones, so I built this tool to convert between them quickly and efficiently. 1. Add the cities you want to convert between (this is saved…

Nowadays, you can get a free VM from some providers (GCP) and there are lots of sites where you can deploy a static website for free (github pages). I'd argue deploying something f…