Metraipolis › archive › dc_d2666a668e06
Fully Interpretable Minimal Transformers: From Geometry to Algorithm — arXiv:2610.09838
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09838
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:11:31.318Z
- SHA-256 of the archived text
d0b5aa0f017ea0116f5845d7dfabb0e2d421af6abab91a7e146dd318568e9d66- Stable URL of this page
https://metraipolis.com/documento/dc_d2666a668e06
How to cite
Fully Interpretable Minimal Transformers: From Geometry to Algorithm — arXiv:2610.09838 — arXiv (en), https://arxiv.org/abs/2610.09838 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2666a668e06 (Metraipolis archive dc_d2666a668e06, sha256 d0b5aa0f017ea0116f5845d7dfabb0e2d421af6abab91a7e146dd318568e9d66)
BibTeX
@misc{dcd2666a668e06,
title = {Fully Interpretable Minimal Transformers: From Geometry to Algorithm — arXiv:2610.09838},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09838},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2666a668e06; sha256 d0b5aa0f017ea0116f5845d7dfabb0e2d421af6abab91a7e146dd318568e9d66},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09838. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present a framework for building and interpreting minimal transformer models. By constraining a transformer's embedding dimension and head size to 2, we enable full two-dimensional visualization of its internal representations. Embeddings, query/key/value transforms, attention outputs, residual streams, and decision boundaries can all be seen directly. Our central claim is that the learned geometry implies an algorithm; the arrangement of points and boundaries in R^2 can be read as a step-by-step procedure. We train a transformer on a simple task where it must produce the most recently observed even number whenever the '+' operator appears in a sequence of digits. Once trained, we visually walk through every step of the transformer's computation. We show how the model embeds the tokens and their respective positions in the sequence, transforms them via the Q, K, and V matrices, uses the dot product between the Q and K representations to form the attention matrix, and uses the attention matrix to select values that move the representation of each input token to the region of the domain of the output layer that will correctly predict the next token. We introduce a suite of interpretability visualizations that make the algorithmic interpretation of this procedure explicit. Our framework offers a pedagogical and experimental testbed to explore how transformers use informational geometry to implement next-token prediction. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.09838 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:14:06.131Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).