WRITE · TRACE · UNDERSTAND
Layer Normalization
Normalize within one token’s feature vector, using population variance and epsilon inside the square root.
Your experiment
layer_norm(values, gain, bias, epsilon) returns per-feature gain*(x-mean)/sqrt(variance+epsilon)+bias. Inputs are nonempty with matching widths; epsilon > 0.
Python runs in your browser. Your draft stays on this device.
What to look for
Normalize within one token’s feature vector, using population variance and epsilon inside the square root. Learned gain and bias then restore useful scale.
Watch your code work
Ready to experimentWrite a solution or load the worked answer, then choose Trace & check.
Step through arrays, variables and training curves produced by your own Python.