# Geospatial Mechanistic Interpretability of Large Language Models

arXiv: https://arxiv.org/abs/2505.03368 · HTML: https://mlsanity.com/paper/2505.03368/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 42 of its 68 references that are in the map.
- First posted on arXiv 6 May 2025.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [Do NLP Models Know Numbers? Probing Numeracy in Embeddings](https://mlsanity.com/paper/1909.07940/) (2019)
- [Probing Pretrained Language Models for Lexical Semantics](https://mlsanity.com/paper/2010.05731/) (2020)
- [Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs](https://mlsanity.com/paper/2402.14903/) (2024)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [Autonomous GIS: the next-generation AI-powered GIS](https://mlsanity.com/paper/2305.06453/) (2023)
- [Pooling Methods in Deep Neural Networks, a Review](https://mlsanity.com/paper/2009.07485/) (2020)
- [Probing What Different NLP Tasks Teach Machines about Function Word Comprehension](https://mlsanity.com/paper/1904.11544/) (2019)
- [Discourse Probing of Pretrained Language Models](https://mlsanity.com/paper/2104.05882/) (2021)
- [Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs](https://mlsanity.com/paper/2311.14656/) (2023)
- [Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages](https://mlsanity.com/paper/2310.09340/) (2023)
- [Are Large Language Models Geospatially Knowledgeable?](https://mlsanity.com/paper/2310.13002/) (2023)
- [GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots](https://mlsanity.com/paper/2404.15500/) (2024)
- [CityGPT: Empowering Urban Spatial Cognition of Large Language Models](https://mlsanity.com/paper/2406.13948/) (2024)
- [Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark](https://mlsanity.com/paper/2401.03991/) (2024)
- [Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs](https://mlsanity.com/paper/2304.11164/) (2023)
- [Do Language Models Know the Way to Rome?](https://mlsanity.com/paper/2109.07971/) (2021)
- [Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation](https://mlsanity.com/paper/2404.01855/) (2024)

## Built on by (most cited first, 2 of 2)

- [Explaining Large Language Models with gSMILE](https://mlsanity.com/paper/2505.21657/) (2025)
- [Interaction Locality in Hierarchical Recursive Reasoning](https://mlsanity.com/paper/2605.20784/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their deployment as knowledge bases and "reasoning" tools remains an area of ongoing research. In geography, a growing body of literature has been focusing on evaluating LLMs' geographical knowledge and their ability to perform spatial reasoning. However, very little is still known about the internal functioning of these models, especially about how they process geographical information. In this chapter, we establish a novel framework for the study of geospatial mechanistic interpretability - using spatial analysis to reverse engineer how LLMs handle geographical information. Our aim is to advance our understanding of the internal representations that these complex models generate while processing geographical information - what one might call "how LLMs think about geographic information" if such phrasing was not an undue anthropomorphism. We first outline the use of probing in revealing internal structures within LLMs. We then introduce the field of mechanistic interpretability, discussing the superposition hypothesis and the role of sparse autoencoders in disentangling polysemantic internal representations of LLMs into more interpretable, monosemantic features. In our experiments, we use spatial autocorrelation to show how features obtained for placenames display spatial patterns related to their geographic location and can thus be interpreted geospatially, providing insights into how these models process geographical information. We conclude by discussing how our framework can help shape the study and use of foundation models in geography.