Splashery

Playground
Looped Transformer, a still.

AI and Computing · Built from a recipe

Looped Transformer

E♭4 on the minor comb. Its drum rings at 298.8 Hz.

Turn it in the PlaygroundTap the picture to strike it.

A looped transformer runs the same transformer block again and again, feeding its output back in as its next input, instead of stacking many different layers.

Shelf
AI and Computing
Kind
Built from a recipe
Sound
Yes
Licenses
Own work (made in the page)

Its note

Splashery stretches a drumhead over this Splash's outline, twelve inches across, and finds the ways it can ring. Its lowest is 298.8 Hz, 70 cents flat of E♭4, the nearest tine on the comb. The next fifteen are its overtones, and each one draws its own figure: sand gathers on the lines that stay still.

The sixteen ways Looped Transformer's drum can ring, lowest first.
  1. 1299 Hz
  2. 2428 Hz
  3. 3513 Hz
  4. 4581 Hz
  5. 5598 Hz
  6. 6715 Hz
  7. 7743 Hz
  8. 8745 Hz
  9. 9805 Hz
  10. 10852 Hz
  11. 11897 Hz
  12. 12913 Hz
  13. 13977 Hz
  14. 141001 Hz
  15. 151010 Hz
  16. 161028 Hz

How to play

Tap it: the tiles loop through one block, sharper each lap, until 3 + 4 = 7.

Its controls

ControlKindRangeStart
Loop until it's sureTap
ThinkButton
ViewList2 choicesPoster (2D)

About it

A looped transformer runs the same transformer block again and again, feeding its output back in as its next input, instead of stacking many different layers. Each pass through the loop can refine the answer a little more, a bit like checking your work, so a small model can spend longer thinking about a harder problem.

Tap it: five tiles ride three laps around a track through one block. Each pass sharpens every tile one step, from noise to a blocky mosaic, to nearly right, to exact, until “3 + 4 = 7” settles with the 7 in gold. Pick the poster or a 3D model in the Splash tab.

Details

Splats
Opens at 200,000 at Mid Detail, 56,377 at Low, and up to 660,000 at Max

Is it right?

Repeating one block is a valid idea in recurrent transformer designs. Here three laps reveal stored pictures of 3 + 4 = 7; no transformer block or arithmetic inference runs.

  1. Simplified

    Transformer computation can repeat across depth.1

    The single block and returning track illustrate a recurrent-depth architecture.

  2. Correct

    The splash ends with the correct arithmetic statement 3 + 4 = 7.2

    The five stored marks are 3, +, 4, =, 7; the last tile images contain only finished bitmap values.

  3. Simplified

    The three laps illustrate refinement rather than learned reasoning.1

    Each lap chooses another stored bitmap level, with no attention, recurrent tensor update, or learned stopping rule.

  1. 1Universal Transformers, Dehghani and coauthors, 2018
  2. 2Multilayer perceptrons, Dive into Deep Learning authors
Simplified
The noise, coarse, nearly finished, and exact tile images are prepared stages. The lap count is fixed at three and is not chosen by difficulty.

Sources and credits

Made in Splashery. Its code is MIT.

Share it

This link opens it in the Playground. To put it on your own page, add the element and one script tag. Every option.

https://splashery.app/play/?toy=looped-transformer<script type="module" src="https://splashery.app/play/src/element.js"></script> <splashery-toy toy="looped-transformer"></splashery-toy>

Nearby on the strip