Concept
Looped transformers
Looped transformers apply the same transformer block repeatedly across depth, rather than stacking many distinct blocks with separate weights. Think of a standard N-layer transformer, except all N layers share one set of parameters, so the forward pass becomes a loop: `h…
The rest of “Looped transformers” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→