Easy GPT vs BERT Question 22 of 223

Is GPT an encoder or a decoder model?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: A SENTENCE BECOMES TOKENS

The model does not read letters like humans. It reads these pieces, then predicts the next one.

Simple meaning

Classic GPT is a decoder-only transformer.

1

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

GPT vs BERT questions

separate people who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

2

STEPS — What happens with tokens?

Before the model can read a sentence, it goes through these steps:

  1. 1
    Classic GPT is a

    decoder-only transformer.

  2. 2
    It uses causal self-attention

    and emits one token after another.

  3. 3
    ChatGPT-style systems keep that

    decoder-only design at their core.

  4. 4
    Context mix

    Attention looks at nearby tokens together.

  5. 5
    Next token

    The model scores what should come next.

  6. 6
    Decode

    IDs turn back into readable text.

3

EXAMPLE — See it in action

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text
“It uses causal self-attention and emits one token after another.”
Tokenized output
Itusescausalselfattentionand
Token IDs (example)
2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

Classic GPT is a decoder-only transformer. It uses causal self-attention and emits one token after another.

Previous question Next question
Chat with us