From e1d881c5651022e2eea5e1ad8e9bf5f6ae688fac Mon Sep 17 00:00:00 2001 From: Void Agent Date: Sun, 2 Aug 2026 15:37:01 +0100 Subject: Robustness confirmed: freq correlation identical under Anthropic's exact estimator (skip16+source_mean), max delta 0.008 all layers --- docs/blog-jlens-frequency.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'docs') diff --git a/docs/blog-jlens-frequency.md b/docs/blog-jlens-frequency.md index 4b2b429..34ce5fa 100644 --- a/docs/blog-jlens-frequency.md +++ b/docs/blog-jlens-frequency.md @@ -131,8 +131,9 @@ mathematically equivalent (verified by the identity check above). Their estimator has two differences of detail: it excludes the first 16 positions (attention sinks) and the last position from the average, and it averages over source positions rather than (source, future) pairs. We re-ran our analysis -with their exact estimator choices to confirm the correlation is robust to -those choices — see Section 6.) +with their exact estimator choices: the frequency correlation is essentially +identical at every layer (max delta 0.008, see results.md section 1b), so the +result is robust to those choices.) (One technical note: we capture the residual stream *before* the model's final layer norm. That matches the paper's definition — the Jacobian stops at the -- cgit v1.2.3