Ride the residual stream
Step \o/ from station to station. It rides the last token of the sequence; each block reads the whole stream (causally) and adds to it. Watch the vector it carries change, and see what it looked at.
the residual stream
what \o/ looked at
Real, and honestly small
What's real
A genuine forward pass in miniature: a 4-dimensional residual stream, one causal attention head whose weights are a true probability distribution, three pre-norm blocks, a real MLP, a real unembed. python selftest.py proves — no network — the attention is a distribution, the mask is causal, the pass is deterministic, and the stream really moves.
What it isn't
It is not a language model and makes no claim about any real model's internals. It shows the shape of the computation — what "through the weights" means — so the leak that crosstalk watches for has somewhere to live in your head. It detects nothing.
forward.py (the real toy pass) · selftest.py (distribution · causal · deterministic, no network). The page runs the same computation client-side.