Skip to content
STIMSMITH

GELU Activation

Technique
First seen 9/15/2026
Last seen 9/15/2026
Evidence 1 chunks

NEIGHBORHOOD

No graph connections found for this entity yet. It may appear in future ingestion runs.

explore full graph →

RELATIONSHIPS

2 connections
Transformer Language Model ← uses 100% 1e
The transformer model uses GELU activation in its feed-forward layers.
DeepVerifier ← uses 100% 1e
DeepVerifier's feed-forward network uses GELU activation function.