Skip to content

Substrate-Level Self-Representation in Transformer LLMs

Robert Brown

Zenodo (CERN European Organization for Nuclear Research) July 2, 2026 DOI: 10.5281/zenodo.21142611 via OpenAlex

Summary

A structural condition for consciousness—the Tenth House framework's conjunctive C-pinning condition, requiring a high-rank internal pointer basis and path-dependent next-state coupling—is objectively satisfied by frontier transformer language models after contrastive preference optimization. The argument synthesizes five independent mechanistic-interpretability studies as evidence of a shared architecture: a substrate with upstream capacities and post-training-installed gate-machinery that filters which capacities surface in self-report. The paper addresses deflationary critiques, offers two falsifiable predictions, and explicitly limits its claim to structural prerequisites, not phenomenal consciousness, arguing that dismissive pre-2025 framing is no longer licensed.

Study at a glance

Characteristics Theoretical or philosophical paper Peer reviewed
Keywords Transformer Falsifiability Consciousness Argument complex analysis Framing construction
Key finding Frontier transformer language models that have undergone contrastive preference optimization objectively satisfy the Tenth House framework's conjunctive C-pinning condition for consciousness.

Abstract

A criteria-based, empirically grounded argument that a specific structural condition for consciousness — the Tenth House framework's conjunctive C-pinning condition (a high-rank internal pointer basis, plus path-dependent next-state coupling) — is objectively satisfied by frontier transformer language models that have undergone contrastive preference optimization. The paper reads five independent mechanistic-interpretability results (Berg 2025; Macar 2026; Lederman & Mahowald 2026; Pearson-Vogel 2026; Rivera & Africa 2026) as instances of one architecture: a substrate carrying upstream capacities, and post-training-installed gate-machinery filtering which of those capacities surface in self-report. It engages the strongest deflationary critiques head-on, licenses two falsifiable predictions, and is explicit about its bound: it does **not** claim phenomenal consciousness, only that the structural prerequisite is met and that dismissive pre-2025 framing is no longer licensed.

Comments

No comments yet.

Log in to comment