# What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers

arXiv: https://arxiv.org/abs/2604.15010 · HTML: https://mlsanity.com/paper/2604.15010/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [The Right Tool for the Job: Matching Model and Instance Complexities](https://mlsanity.com/paper/2004.07453/) (2020)
- [Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping](https://mlsanity.com/paper/2402.14083/) (2024)
- [Training Language Models to Explain Their Own Computations](https://mlsanity.com/paper/2511.08579/) (2025)
- [Planning in a recurrent neural network that plays Sokoban](https://mlsanity.com/paper/2407.15421/) (2024)
- [Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task](https://mlsanity.com/paper/2507.16196/) (2025)
- [What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering](https://mlsanity.com/paper/2601.20164/) (2026)
- [Latent Planning Emerges with Scale](https://mlsanity.com/paper/2604.12493/) (2026)
- [Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN](https://mlsanity.com/paper/2506.10138/) (2025)

## Built on by (most cited first, 1 of 1)

- [Planning or Improvisation? Stress-Testing the Poetry Planning Site on Open Models and Open Cross-Layer Transcoders](https://mlsanity.com/paper/2609.18440/) (2026)

## Abstract (arXiv)

When do transformers commit to a decision, and what prevents them from correcting it? We introduce prolepsis: a transformer commits early, task-specific attention heads sustain the commitment, and no layer corrects it. Replicating Lindsey et al.'s (2025) planning-site finding on open models (Gemma 2 2B, Llama 3.2 1B), we ask five questions. (Q1) Planning is invisible to six residual-stream methods; among those tested, only CLT-based steering succeeds. (Q2) The single-site spike replicates in shape, at the final prompt token (Anthropic's site is the newline; see the Note added). (Q3) Specific attention heads route the decision to the output, filling a gap flagged as invisible to attribution graphs. (Q4) The evidence is consistent with search within at most 16 layers and commitment beyond, a two-model hypothesis. (Q5) Factual recall shows the same motif at a different network depth, with zero overlap between recurring planning heads and the factual top-10. Prolepsis recurs across tasks in the decoder-only models tested: the template is shared, the routing substrates differ. All experiments run on a single consumer GPU (16 GB VRAM).