Gen AI Lingo

Your next step

From hidden states to an answer

Vocabulary, scores, the output head, targets and stop reasons.

Start learning

What you’ll learn

  1. The output vocabulary

    Identify the set of token choices at a generation step.

    About 4 minutes · Open activity

  2. Logits are scores before probabilities

    Distinguish raw output scores from normalized probabilities.

    About 4 minutes · Open activity

  3. The language-model head

    Locate the mapping from a hidden representation to vocabulary scores.

    About 4 minutes · Open activity

  4. Predicting the next training token

    Identify the target used at one position during next-token training.

    About 4 minutes · Open activity

  5. Token loss rewards the observed target

    Explain why assigning the observed target less probability increases loss.

    About 4 minutes · Open activity

  6. A turn can stop for different reasons

    Distinguish a natural stop from an output-budget limit.

    About 4 minutes · Open activity

  7. Remembered patterns can include memorization

    Distinguish learned generalization from reproducing training material.

    About 4 minutes · Open activity

  8. Trace one generated token

    Label representation, output scores, sampling choice and completion status in a fictional decoder trace, and identify one uncertainty about provenance.

    About 5 minutes · Open activity