Concept
Context window
The context window is the maximum span of text a language model can attend to at once, measured in tokens (not characters or words). Everything the model uses to produce its next token, the prompt, any prior conversation, retrieved documents, and its own generated output so…
The rest of “Context window” 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→