<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Transformers on McKuzyk</title><link>https://mckuzyk.com/tags/transformers/</link><description>Recent content in Transformers on McKuzyk</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 21 Apr 2026 10:31:12 -0700</lastBuildDate><atom:link href="https://mckuzyk.com/tags/transformers/index.xml" rel="self" type="application/rss+xml"/><item><title>Waves All the Way Down</title><link>https://mckuzyk.com/posts/transformers-grokking-modular-arithmetic/</link><pubDate>Tue, 21 Apr 2026 10:31:12 -0700</pubDate><guid>https://mckuzyk.com/posts/transformers-grokking-modular-arithmetic/</guid><description>How a transformer learns to compute modular addition, and what it reveals about generalization</description></item></channel></rss>