Reference 3 stops to get here · leads to 1

Padding Token

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

Your route here

3 stops · basics first
  1. Token ✓ understood

    The basic unit of text that a language model processes, typically representing a word, subword, or character. Tokens are the fundamental building blocks for LLM input and output.

  2. Tokenization ✓ understood

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

  3. Special Token ✓ understood

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

  4. Padding Token · you are here ✓ understood

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

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

  • Special Token
  • Batching
  • Attention Mask

Where it sits

Before this

Special Token
Padding Token

Leads to

Attention Mask

Explore nearby

Language & LLMs Attention Mask A binary mask indicating which tokens should be attended to, used to handle padding and causal masking. Training Batch Size The number of training examples processed together in one forward/backward pass. Language & LLMs BOS Token Beginning Of Sequence token - marks the start of a sequence in language models. Language & LLMs EOS Token End Of Sequence token - signals when the model has finished generating a complete output.