Skip to content
AImpact
IT EN
Models Intermediate Also known as: Encoding posizionale · Codifica posizionale

Positional Encoding

Information added to every token to tell the model where it sits in the sequence, because plain attention has no sense of order.

ShareLinkedInX

In practice

Without positional encoding "dog bites man" and "man bites dog" would mean the same to the model. Early versions used sine/cosine functions; today most LLMs use RoPE because it extends better to long contexts.

Related terms

Transformer Attention RoPE Context window

Seen in the wild

0 entries mentioning it

No archive entry mentions it explicitly. Appears in broader contexts.

← All terms