https://www.msuiche.com/tags/mechanistic-interpretability/Recent content in Mechanistic Interpretability on Matt SuicheHugoen-usSun, 16 Aug 2026 00:00:00 +0200https://www.msuiche.com/posts/autoresearch-abliteration-without-redistributing-the-model/Sun, 16 Aug 2026 00:00:00 +0200https://www.msuiche.com/posts/autoresearch-abliteration-without-redistributing-the-model/<p>I have been travelling too much this year to see the inside of a gym, so I am pleased to report that I am finally lifting weights again. Different weights. Considerably less cardio.</p> <h2 id="tldr">TL;DR<a href="#tldr" class="anchor" aria-label="Link to TL;DR">#</a></h2> <p>If you want to change what a model refuses, the usual approach is to edit its weights and upload the result. That is what every &ldquo;uncensored&rdquo; checkpoint you have seen is: a full re-upload, differing from the original by a rounding error spread thinly across a few hundred matrices.</p>