Easy Transformers Question 14 of 223

What is positional encoding?

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

Attention itself has no sense of order, so the model needs position signals.

WHY — Tokens instead of words?

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

Transformers 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.

STEPS — What happens with tokens?

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

1
Attention itself has no
sense of order, so the model needs position signals.
2
Positional encodings or rotary
embeddings inject where each token sits in the sequence.
3
Without them, 'dog bites
man' and 'man bites dog' would look too similar.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

EXAMPLE — See it in action

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

Input text

“Positional encodings or rotary embeddings inject where each token sits in the se”

Tokenized output

Positionalencodingsorrotaryembeddingsinject

Token IDs (example)

2987408337471632900

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

Key takeaway

Attention itself has no sense of order, so the model needs position signals. Positional encodings or rotary embeddings inject where each token sits in the sequence.