● WRITING · 4 NOTES · PROSE AND EVIDENCE, SAME PIPELINE

Notes & write-ups

Write-ups from the bench — what worked, what collapsed under a corrected protocol, and the gates that caught it. The charts inside each post render from the same pinned results files as everything else on this site.

Feature of the Day: A Gemma SAE AtlasA daily tour through the interpretable features hiding inside Gemma 2 (2B). Day 1 builds the pipeline: a Gemma Scope sparse autoencoder with 16,384 features reads layer 12, fires a median of 72 of them per token, and leaves 51 percent dormant on a 40-prompt probe. Its sharpest direction, feature 4667 (peak activation 393), is a sentence-initial discourse-marker detector that lights up on 'Therefore', 'According' and 'A' and stays near zero everywhere else.interpretabilitysparse-autoencodersgemmagemma-scopemechanistic-interpretabilitykaggleKilling the 10 GB TensorMy 596M-parameter model's single biggest training tensor was a 9.96 GB fp32 logit matrix that exists only to be reduced to one scalar. On a free Kaggle T4, fused cross-entropy deletes it: the naive path OOMs past 4,096 tokens while Liger holds flat at ~3.2 GB out to 32,768, agreeing with the fp32 reference to ~1e-7.cudamemorycross-entropyligerkaggleqwen3-0.6bThe Win That Was NotMy SFT ablation produced a +0.68-perplexity win with a confidence interval tight enough to look unimpeachable. It was an artifact of scoring the two arms on different token sets, and it collapsed to +0.009 on a fixed held-out set.qwen3-0.6bsftevaluationreproduce-then-attributeWhat the Gates CaughtSeven ways my own study tried to fool me (a token-soup data loader, an eval-token confound, a misread smoke log, a conflated data ratio) and the mechanical checks that caught each one before it became a claim.qwen3-0.6bmethodologypre-registrationreproduce-then-attribute
Numbers in prose are rounded; the charts are not./research has every number →