# Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

arXiv: https://arxiv.org/abs/2406.00877 · HTML: https://mlsanity.com/paper/2406.00877/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 2 Jun 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [Emergent Linear Representations in World Models of Self-Supervised Sequence Models](https://mlsanity.com/paper/2309.00941/) (2023)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Future Lens: Anticipating Subsequent Tokens from a Single Hidden State](https://mlsanity.com/paper/2311.04897/) (2023)
- [Jump to Conclusions: Short-Cutting Transformers With Linear Transformations](https://mlsanity.com/paper/2303.09435/) (2023)
- [ChessGPT: Bridging Policy Learning and Language Modeling](https://mlsanity.com/paper/2306.09200/) (2023)
- [Chess as a Testbed for Language Model State Tracking](https://mlsanity.com/paper/2102.13249/) (2021)
- [Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models](https://mlsanity.com/paper/2403.15498/) (2024)
- [A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task](https://mlsanity.com/paper/2402.11917/) (2024)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [The Chess Transformer: Mastering Play using Generative Language Models](https://mlsanity.com/paper/2008.04057/) (2020)

## Built on by (most cited first, 30 of 34)

- [ICLR: In-Context Learning of Representations](https://mlsanity.com/paper/2501.00070/) (2024)
- [Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2406.16033/) (2024)
- [Transformers Struggle to Learn to Search](https://mlsanity.com/paper/2412.04703/) (2024)
- [Planning in a recurrent neural network that plays Sokoban](https://mlsanity.com/paper/2407.15421/) (2024)
- [How Do LLMs Use Their Depth?](https://mlsanity.com/paper/2510.18871/) (2025)
- [Mastering Chess with a Transformer Model](https://mlsanity.com/paper/2409.12272/) (2024)
- [Transformers Use Causal World Models in Maze-Solving Tasks](https://mlsanity.com/paper/2412.11867/) (2024)
- [Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2602.11180/) (2026)
- [On Logical Extrapolation for Mazes with Recurrent and Implicit Networks](https://mlsanity.com/paper/2410.03020/) (2024)
- [Chessformer: A Unified Architecture for Chess Modeling](https://mlsanity.com/paper/2605.19091/) (2026)
- [Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN](https://mlsanity.com/paper/2506.10138/) (2025)
- [Predicting Chess Puzzle Difficulty with Transformers](https://mlsanity.com/paper/2410.11078/) (2024)
- [K-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks](https://mlsanity.com/paper/2505.12268/) (2025)
- [Detecting and Characterizing Planning in Language Models](https://mlsanity.com/paper/2508.18098/) (2025)
- [Exploring Human-AI Conceptual Alignment through the Prism of Chess](https://mlsanity.com/paper/2510.26025/) (2025)
- [ParaScopes: What do Language Models Activations Encode About Future Text?](https://mlsanity.com/paper/2511.00180/) (2025)
- [Tracing the Thought of a Grandmaster-level Chess-Playing Transformer](https://mlsanity.com/paper/2604.10158/) (2026)
- [Mixture of Masters: Sparse Chess Language Models with Player Routing](https://mlsanity.com/paper/2602.04447/) (2026)
- [Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions](https://mlsanity.com/paper/2605.07984/) (2026)
- [Interaction Locality in Hierarchical Recursive Reasoning](https://mlsanity.com/paper/2605.20784/) (2026)
- [Latent Programming Horizons in Coding Agents](https://mlsanity.com/paper/2607.05188/) (2026)
- [Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States](https://mlsanity.com/paper/2607.18589/) (2026)
- [Exploring Collaboration between a language and a non-language agent](https://mlsanity.com/paper/2609.00474/) (2026)
- [Understanding the learned look-ahead behavior of chess neural networks](https://mlsanity.com/paper/2505.21552/) (2025)
- [Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Tasks](https://mlsanity.com/paper/2512.12792/) (2025)
- [Abstract Concept Modelling in Conceptual Spaces: A Study on Chess Strategies](https://mlsanity.com/paper/2601.21771/) (2026)
- [Large Language Models Can Take False First Steps at Inference-time Planning](https://mlsanity.com/paper/2602.02991/) (2026)
- [Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors](https://mlsanity.com/paper/2603.14087/) (2026)
- [A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners](https://mlsanity.com/paper/2606.03685/) (2026)
- [Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess](https://mlsanity.com/paper/2608.27757/) (2026)

## Abstract (arXiv)

Do neural networks learn to implement algorithms such as look-ahead or search "in the wild"? Or do they rely purely on collections of simple heuristics? We present evidence of learned look-ahead in the policy network of Leela Chess Zero, the currently strongest neural chess engine. We find that Leela internally represents future optimal moves and that these representations are crucial for its final output in certain board states. Concretely, we exploit the fact that Leela is a transformer that treats every chessboard square like a token in language models, and give three lines of evidence (1) activations on certain squares of future moves are unusually important causally; (2) we find attention heads that move important information "forward and backward in time," e.g., from squares of future moves to squares of earlier ones; and (3) we train a simple probe that can predict the optimal move 2 turns ahead with 92% accuracy (in board states where Leela finds a single best line). These findings are an existence proof of learned look-ahead in neural networks and might be a step towards a better understanding of their capabilities.