Differences

This shows you the differences between two versions of the page.

--- software:ai:transformers [2026/05/06 17:01] – created ron
+++ software:ai:transformers [2026/05/06 17:02] (current) – ron
@@ Line 1: / Line 1: @@
+# Mechanistic Interpretability in Transformers
+## Circuits, neurons, feature superposition & reverse-engineering model behaviour
 from [[https://billionhopes.ai/mechanistic-interpretability-in-transformers/|Billion Hopes AI]]
----
-Mechanistic Interpretability in Transformers
-Circuits, neurons, feature superposition & reverse-engineering model behaviour
-Introduction
+### Introduction
 Modern AI systems – especially transformer-based models – can generate human-like text, solve complex problems, and even reason across domains. Yet, despite their impressive capabilities, they often behave like “black boxes.” We can see what goes in and what comes out, but we don’t fully understand how they arrive at their answers.