https://www.ronreynolds.com/wiki/ 2026-06-13T13:30:54+00:00 https://www.ronreynolds.com/wiki/ https://www.ronreynolds.com/wiki/lib/exe/fetch.php?media=wiki:dokuwiki.svg text/html 2026-05-07T00:29:51+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.ronreynolds.com/wiki/doku.php?id=software:ai:llm&rev=1778113791&do=diff copied from Build a Large Language Model (From Scratch) by Sebastian Raschka (ISBN 9781633437166) 1 Understanding large language models This chapter covers * High-level explanations of the fundamental concepts behind large language models (LLMs) * Insights into the transformer architecture from which LLMs are derived text/html 2026-05-06T17:02:27+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.ronreynolds.com/wiki/doku.php?id=software:ai:transformers&rev=1778086947&do=diff Mechanistic Interpretability in Transformers Circuits, neurons, feature superposition & reverse-engineering model behaviour from Billion Hopes AI 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.…