aifree.dev

What's inside the box?

The Transformer · Builder · 5 min · transformer, attention, llm · after Self-attention

A Transformer is a stack of identical layers. Each layer runs attention (who matters to whom) and then a small "think" step on every piece, and the stack repeats that dozens of times before producing odds for the next piece.

Before you start: could you explain this to a friend?

1 = not at all · 5 = easily

  1. 1 Guess first

    Inside the model, how many different kinds of machinery are there?
  2. 2 Look

    The same trick, twelve times

    1 / 3
    it

    One piece — "it" — enters the first layer carrying only what it is: a word and a position.

    One piece changes colour with every ring: the same two moves, repeated, rewrite what the piece means here.

  3. Attention lets each piece gather from the others; the "think" step (a small neural net, the MLP) works on what it gathered. Stack that a dozen times and a piece ends up carrying the whole sentence’s context — then the last layer turns it into odds.

  4. 4 You are the model

    Put the four blocks in the order a piece meets them, then Check.

    1. Think (MLP)work on what attention found
    2. Next piece oddsthe loaded wheel
    3. Embeddingpiece → numbers
    4. Attentionwho matters to whom

    × 12: the middle two repeat, layer after layer

    Put the four blocks in the order a piece meets them.
  5. 5 Check

    Where do the odds for the next piece come from?
  6. 6 Say it back

  7. 7 Mission · 2 min

    Go back to the Journey, type your own sentence and scroll through the layers station slowly. Count the rings and watch the piece change colour.

Three quick ones

Drawn at random from this lesson's pool; different next time.

Done?

Now: could you explain this to a friend?

1 = not at all · 5 = easily

Answer the three quick ones first.

Sources

Published Oct 20, 2026 · updated Oct 20, 2026

Embed this

Paste this into a blog post or course page: the lesson's main picture in an iframe, with a link back to the full lesson.

<iframe src="https://aifree.dev/embed/explain/transformer" width="100%" height="620" style="border:0;max-width:720px" title="What's inside the box? (aifree.dev Explain)" loading="lazy"></iframe>
<p><a href="https://aifree.dev/explain/transformer">What's inside the box? Interactive lesson on aifree.dev</a></p>

Never miss new offers and news

New tools, credits, and AI news are added regularly. Pick how you want to hear about them.

Telegram channel
Join @aifree_dev and get new free AI offers and news right in your Telegram feed.
Browser notifications
Turn on push notifications and get an alert on this device whenever something new is posted. No account needed.
Email newsletter
A weekly digest of new, changed and expiring free AI offers. Double opt-in, one-click unsubscribe.

Unsubscribe anytime. Privacy

Frequently asked questions

What is aifree.dev?

aifree.dev helps everyone access AI through a curated directory of free AI tools, API credits, free tiers, and startup programs for coding, image, voice, video, and students - verified regularly.

How are offers presented?

Each offer includes its access details, free models when available, and expiration information when provided. Limited-time deals stay visible so they are easy to compare.

Do education and startup programs need verification?

Yes. Providers usually ask students to verify their status with a school email, student ID, or a program like the GitHub Student Pack, and ask startups to verify company details such as age, funding, or website. Check each offer’s claim page for the exact requirements.

What kinds of free AI offers are listed?

Free tiers and free trials from AI providers, free API credits, startup and student programs, and free tools for coding, image generation, voice, and video.

How can I suggest a tool or report a broken link?

Use the submit form: paste the offer page URL and a short note. A person checks every submission before anything is listed. Broken links and changed terms go through the same form.

+

Know a good one?

Tell us about an AI tool worth knowing. Found a broken link? We want to hear that too.

Submit an offer