ffn-layers-contain-most-transformer-parameters

IN premiseentries/2026/06/21/wiki-Transformer_deep_learning_architecture-chunk-2.md

Created 2026-06-21T09:50:11+00:00

Feed-forward layers (not attention layers) contain the majority of parameters in a transformer model.

Summary

In a transformer, the bulk of its learned weights live in the feed-forward blocks rather than in the attention heads. This matters because most of the model's capacity and stored knowledge sits in those dense linear layers, so decisions about compression, pruning, or targeted modification should focus there first.

Dependents

These beliefs depend on this one: