<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Distributed Representation on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/distributed-representation/</link>
    <description>Recent content in Distributed Representation on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 07 Sep 2026 10:00:00 +0000</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/distributed-representation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Dimensions Do Not Mean What You Think</title>
      <link>http://programmer.ie/books/embeddings-from-first-principles/05-chapter/</link>
      <pubDate>Mon, 07 Sep 2026 10:00:00 +0000</pubDate>
      <guid>http://programmer.ie/books/embeddings-from-first-principles/05-chapter/</guid>
      <description>&lt;p&gt;&lt;em&gt;Part II — Inside the Space&lt;/em&gt;&lt;/p&gt;&#xA;&lt;h2 id=&#34;what-does-dimension-173-mean&#34;&gt;What does dimension 173 mean?&lt;/h2&gt;&#xA;&lt;p&gt;Pull the 173rd coordinate of every vector in your corpus and sort. You get a list of documents ordered by&amp;hellip; something. Occasionally a coordinate is weakly interpretable — &amp;ldquo;this one seems higher for questions&amp;rdquo; — but usually the sorted list has no human-nameable theme. Dimension 173 does not mean &amp;ldquo;formality&amp;rdquo; or &amp;ldquo;sentiment&amp;rdquo; or &amp;ldquo;is about sports.&amp;rdquo;&lt;/p&gt;&#xA;&lt;p&gt;And yet the vector works. Similarity search returns sensible results. The structure is there; it is just not living in the individual axes.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
