AnimatedLLM: Explaining LLMs with Interactive Visualizations

Zdeněk Kasner; Ondřej Dušek

AnimatedLLM: Explaining LLMs with Interactive Visualizations

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

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.

Anthology ID:: 2026.teachingnlp-1.1
Volume:: Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)
Month:: March
Year:: 2026
Address:: Rabat, Morocco
Editors:: Matthias Aßenmacher, Laura Biester, Claudia Borg, György Kovács, Margot Mieskes, Sofia Serrano
Venues:: TeachingNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1–6
Language:
URL:: https://aclanthology.org/2026.teachingnlp-1.1/
DOI:
Bibkey:
Cite (ACL):: Zdeněk Kasner and Ondrej Dusek. 2026. AnimatedLLM: Explaining LLMs with Interactive Visualizations. In Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026), pages 1–6, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):: AnimatedLLM: Explaining LLMs with Interactive Visualizations (Kasner & Dusek, TeachingNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.teachingnlp-1.1.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{kasner-dusek-2026-animatedllm-explaining,
    title = "{A}nimated{LLM}: Explaining {LLM}s with Interactive Visualizations",
    author = "Kasner, Zden{\v{e}}k  and
      Dusek, Ondrej",
    editor = {A{\ss}enmacher, Matthias  and
      Biester, Laura  and
      Borg, Claudia  and
      Kov{\'a}cs, Gy{\"o}rgy  and
      Mieskes, Margot  and
      Serrano, Sofia},
    booktitle = "Proceedings of the Seventh Workshop on Teaching Natural Language Processing ({T}each{NLP} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.teachingnlp-1.1/",
    pages = "1--6",
    ISBN = "979-8-89176-375-3",
    abstract = "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."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kasner-dusek-2026-animatedllm-explaining">
    <titleInfo>
        <title>AnimatedLLM: Explaining LLMs with Interactive Visualizations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zdeněk</namePart>
        <namePart type="family">Kasner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Dusek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Matthias</namePart>
            <namePart type="family">Aßenmacher</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Laura</namePart>
            <namePart type="family">Biester</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Claudia</namePart>
            <namePart type="family">Borg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">György</namePart>
            <namePart type="family">Kovács</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Margot</namePart>
            <namePart type="family">Mieskes</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sofia</namePart>
            <namePart type="family">Serrano</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-375-3</identifier>
    </relatedItem>
    <abstract>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.</abstract>
    <identifier type="citekey">kasner-dusek-2026-animatedllm-explaining</identifier>
    <location>
        <url>https://aclanthology.org/2026.teachingnlp-1.1/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1</start>
            <end>6</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T AnimatedLLM: Explaining LLMs with Interactive Visualizations
%A Kasner, Zdeněk
%A Dusek, Ondrej
%Y Aßenmacher, Matthias
%Y Biester, Laura
%Y Borg, Claudia
%Y Kovács, György
%Y Mieskes, Margot
%Y Serrano, Sofia
%S Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-375-3
%F kasner-dusek-2026-animatedllm-explaining
%X 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.
%U https://aclanthology.org/2026.teachingnlp-1.1/
%P 1-6

Download as File

Markdown (Informal)

[AnimatedLLM: Explaining LLMs with Interactive Visualizations](https://aclanthology.org/2026.teachingnlp-1.1/) (Kasner & Dusek, TeachingNLP 2026)

AnimatedLLM: Explaining LLMs with Interactive Visualizations (Kasner & Dusek, TeachingNLP 2026)

ACL

Zdeněk Kasner and Ondrej Dusek. 2026. AnimatedLLM: Explaining LLMs with Interactive Visualizations. In Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026), pages 1–6, Rabat, Morocco. Association for Computational Linguistics.