OpenResearchAlpha

bioRxiv · 20 Nov 2026

Curated annotations locate biological concepts in protein language models from layers to neurons

Logan Halleeh-index 6, Jason P Gleghornh-index 35

0
Citations
no database records one yet
0
Citations in 2026
so far
35
Leading author's h-index
Jason P Gleghorn, in QAI's scholar index
0
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0
  • Europe PMC0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

Interpretability methods describe what a network has learned, yet their claims are rarely tested against model-independent ground truth. We argue that proteins are an ideal modality for interpretability since curators annotate functional sites residue by residue. Across three ESMC protein language models (300M-6B parameters), we show that conclusions depend on where models are read, how concepts are decoded, which units are examined, and how they are scored. Concepts become linearly readable along depth long before erasure impairs masked-token prediction, and 20-fold scaling shifts concept depth more than peak score. Most of a nonlinear probe's lead over a linear one reflects fitting and readout shape rather than nonlinear encoding. Over whole proteins, saturated metrics render feed-forward neurons indistinguishable from random rotations. At annotated residues, dual-signed neuron poles identify 2.5-5.4 times as many concepts as rotations without training, though sparse autoencoders identify more. Without held-out validation, however, shuffled annotations label nearly every latent, and causal reliance emerges in neuron groups rather than single poles. Reading selected intra-block states exposes binding and active sites that stream probes read poorly and lifts a simple probe 5% above the best published MCC on a leakage-controlled interaction benchmark. We recommend reading a model directly against annotation, scoring units where they fire with a measure that is not saturated, and training a dictionary only where it adds coverage.

Bioinformatics

What the data shows

  • No database records a citation yet, as is usual for a paper this new.
  • Jason P Gleghorn has the highest h-index among the authors (35).

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (2)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (0)

What it cites, from open citation data, with Crossref's record of each.

No references in the open citation data yet.