Skip to content

Structure is not mechanism: high-gain gated-FFN rows across text and genomic foundation models

Sep 2026 · 0 citations · 17 references
Biology Computer Science

TL;DR

High-gain gated-FFN rows are a recurrent architectural phenotype whose structural prominence acts as an enrichment signal, not a calibrated measure of functional criticality or a specification of causal organization.

Abstract

A small number of unusually high-gain parameters can exert disproportionate effects in transformer language models, but whether analogous structures recur in genomic foundation models and whether structural geometry determines functional importance remains unknown. We analyzed high-gain rows in gated feed-forward networks across text and genomic foundation models, including a frozen 22-model causal census. Computing an associated bilinear weight operator exactly, without a diagonal approximation, we tested whether structural extremeness is a transferable mechanism. Activation-derived candidates were functionally enriched relative to random and top-norm same-layer controls, yet neither spectral concentration nor operator magnitude predicted causal effect size, and these associations vanished within the endpoint-homogeneous text-decoder subset. A within-layer sweep of 36 rows in one genomic and one text decoder resolved this into two regimes: below the detector's acceptance threshold the ratio carried no positive information about causal damage, whereas above it the ratio ordered rows strongly but did not grade severity as a dose-response. The same sweep revealed a second individually catastrophic row invisible to a one-candidate-per-model census, and non-additive damage among co-located critical rows. Case studies showed divergent causal organizations: a robust super-additive pair interaction in DNABERT-2, and in GENERator a sharply position-localized dependence in which preserving or restoring the row's beginning-of-sequence contribution rescued essentially all native-loss damage. High-gain gated-FFN rows are therefore a recurrent architectural phenotype whose structural prominence acts as an enrichment signal, not a calibrated measure of functional criticality or a specification of causal organization. Enrichment is general, but the mechanism is model-specific.

View source

Similar papers

Open access Sep 2026

Towards Sparse Causal Features for Zero-shot Mutation Effect Prediction in a Protein Language Model

This work provides the first causal, feature-level account of zero-shot mutation effect prediction in a pLM, and introduces a sparse feature circuit framework that combines sparse autoencoders, integrated-gradients attribution, and activation patching to identify the latent features that causally mediate zero-shot muta...

Saishradha Mohanty, Manya Phutela, A. G. Green · 0 citations
#artificial intelligence Preprint Oct 2026

How Language Models Organize Task Information

Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for prediction. We measure readout sparsity with \(k^*\), the smallest feature count found by a fixed search protocol that recovers 95% of dense-probe AUROC above chance. We evaluat...

Kai-Yang Wan, Yu-Xia Wang · 0 citations
Open access Sep 2026

DisenTE: Sparse Pattern–Context Modeling for Interpretable Translation-Efficiency Matrix Completion

DisenTE, a sequence-conditioned neural model that combines separate sequence and context branches with a sparse low-rank pattern–context channel, is presented, a sequence-conditioned neural model that combines separate sequence and context branches with a sparse low-rank pattern–context channel.

Miao-Zhe Huo, Ying-Ying Yu, Shi-Ying Li · 0 citations
#artificial intelligence Preprint Oct 2026

What DNA Foundation Models Learn Beyond Sequence Composition

Do genomic foundation models (FMs) provide predictive information beyond simple sequence composition? We evaluate frozen representations from five DNA FMs against normalized k-mer frequencies across 57 genomic classification datasets and two exploratory gene-expression regression tasks. Simple k-mer features remain com...

Vincenzo Yuto Civale, Andrew D. Bagdanov, Alberto Magi · 0 citations
Open access Sep 2026

Disentangling decoder capacity and directionality in type constrained knowledge graph link prediction

Decoder comparisons in typed knowledge graph (KG) link prediction often confound relation specificity, off-diagonal interactions, and directionality. We separate these factors with four seed-matched decoders applied to GCN, GraphSAGE, and GAT encoders: a shared inner product (IP), a relation-specific diagonal bilinear...

Shi-Ming Feng · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.