# Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models

arXiv: https://arxiv.org/abs/2604.01404 · HTML: https://mlsanity.com/paper/2604.01404/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [From Tokens to Words: On the Inner Lexicon of LLMs](https://mlsanity.com/paper/2410.05864/) (2024)
- [Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs](https://mlsanity.com/paper/2406.20086/) (2024)

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

- [LMs as Task-Specific Knowledge Bases: An Interpretability Analysis](https://mlsanity.com/paper/2606.27237/) (2026)

## Abstract (arXiv)

How do language models retrieve entity-specific facts from their parameters? We investigate this question by searching for sparse, entity-selective MLP neurons - which we call entity cells, by analogy to the "grandmother cell" hypothesis in neuroscience - and testing whether they play a causal role in factual recall. We localize candidate entity cells by ranking MLP neurons for activation consistency across varied prompts about the same entity, applying this procedure across seven models on a curated subset of PopQA. In all models, localized neurons cluster predominantly in early layers, an empirical pattern not imposed by the architecture. Using Qwen2.5-7B base as a model organism, we find the clearest causal evidence: suppressing a localized cell selectively erases recall for its matched entity while leaving others intact, and activating a single cell is sufficient to recover correct knowledge for most entities - even when the entity is absent from the context. The same cells are recovered under aliases, acronyms, misspellings, and multilingual surface forms, and remain stable through instruction tuning, suggesting they encode canonical entity identity rather than surface token patterns. Causal signals vary across model families, pointing to architectural differences in how entity knowledge is organized. These findings offer concrete, interpretable access points for understanding, controlling, and correcting factual knowledge in language models, and draw a surprising empirical parallel to longstanding questions in neuroscience about sparse coding of concepts.