AnimatedLLM: Explaining LLMs with Interactive Visualizations

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kasner, Zdeněk, Dušek, Ondřej
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918315321982976
author Kasner, Zdeněk
Dušek, Ondřej
author_facet Kasner, Zdeněk
Dušek, Ondřej
contents Large language models (LLMs) are becoming central to natural language processing education, yet materials showing their mechanics are sparse. We present AnimatedLLM, an interactive web application that provides step-by-step visualizations of a Transformer language model. AnimatedLLM runs entirely in the browser, using pre-computed traces of open LLMs applied on manually curated inputs. The application is available at https://animatedllm.github.io, both as a teaching aid and for self-educational purposes.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04213
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AnimatedLLM: Explaining LLMs with Interactive Visualizations
Kasner, Zdeněk
Dušek, Ondřej
Computation and Language
Large language models (LLMs) are becoming central to natural language processing education, yet materials showing their mechanics are sparse. We present AnimatedLLM, an interactive web application that provides step-by-step visualizations of a Transformer language model. AnimatedLLM runs entirely in the browser, using pre-computed traces of open LLMs applied on manually curated inputs. The application is available at https://animatedllm.github.io, both as a teaching aid and for self-educational purposes.
title AnimatedLLM: Explaining LLMs with Interactive Visualizations
topic Computation and Language
url https://arxiv.org/abs/2601.04213