Reference 18 stops to get here

Causal Mask

An attention mask ensuring tokens can only attend to previous positions, crucial for autoregressive generation.

Your route here

18 stops · basics first
  1. Natural Language Processing ✓ understood

    The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots.

  2. Token ✓ understood

    The unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary.

  3. Tokenization ✓ understood

    Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it.

  4. Language Modeling ✓ understood

    Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models.

  5. Autoregressive Model ✓ understood

    A model that generates output one token at a time, using previously generated tokens as input for the next prediction.

  6. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  7. Neural Network ✓ understood

    A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.

  8. Dataset ✓ understood

    A collection of data examples used for training, validating, or testing machine learning models.

  9. Feature ✓ understood

    A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model.

  10. Deep Learning ✓ understood

    A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

  11. Representation Learning ✓ understood

    Letting a model learn its own internal description of the data, such as embeddings or layered visual features, instead of relying on features designed by hand.

  12. Embedding ✓ understood

    A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together.

  13. Attention Mechanism ✓ understood

    A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step.

  14. Self-Attention ✓ understood

    An attention step in which every token in a sequence looks at every token in that same sequence and builds a new representation from a weighted mix of them.

  15. Masking ✓ understood

    Hiding some positions from a model, either to control what attention may look at (causal and padding masks) or to create a fill-in-the-blank training task.

  16. Special Token ✓ understood

    Reserved tokens with special meanings like [CLS], [SEP], [MASK], [PAD] used in various model architectures.

  17. Padding Token ✓ understood

    A special token used to make sequences the same length in a batch, typically ignored during computation.

  18. Attention Mask ✓ understood

    A binary mask indicating which tokens should be attended to, used to handle padding and causal masking.

  19. Causal Mask · you are here ✓ understood

An attention mask ensuring tokens can only attend to previous positions, crucial for autoregressive generation.

This concept is essential for understanding large language models and forms a key part of modern AI systems.

  • Attention Mask
  • Autoregressive
  • GPT

Where it sits

Causal Mask

Leads to

Nothing yet: a destination in its own right.

Explore nearby