# Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis

arXiv: https://arxiv.org/abs/2011.12073 · HTML: https://mlsanity.com/paper/2011.12073/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 18 of 18)

- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [On the Transformation of Latent Space in Fine-Tuned NLP Models](https://mlsanity.com/paper/2210.12696/) (2022)
- [How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings](https://mlsanity.com/paper/2109.10179/) (2021)
- [Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models](https://mlsanity.com/paper/2310.00313/) (2023)
- [Structural Similarities Between Language Models and Neural Response Measurements](https://mlsanity.com/paper/2306.01930/) (2023)
- [Probing Semantic Grounding in Language Models of Code with Representational Similarity Analysis](https://mlsanity.com/paper/2207.07706/) (2022)
- [Reconstruction Probing](https://mlsanity.com/paper/2212.10792/) (2022)
- [Quantifying Compositionality of Classic and State-of-the-Art Embeddings](https://mlsanity.com/paper/2509.19332/) (2025)
- [Vocabulary embeddings organize linguistic structure early in language model training](https://mlsanity.com/paper/2510.07613/) (2025)
- [Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models](https://mlsanity.com/paper/2308.08774/) (2023)
- [Implicit Representations of Grammaticality in Language Models](https://mlsanity.com/paper/2605.05197/) (2026)
- [Towards Using Diachronic Distributed Word Representations as Models of Lexical Development](https://mlsanity.com/paper/2105.05091/) (2021)
- [Probing of Quantitative Values in Abstractive Summarization Models](https://mlsanity.com/paper/2210.00667/) (2022)
- [Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers](https://mlsanity.com/paper/2409.14097/) (2024)

## Abstract (arXiv)

As the name implies, contextualized representations of language are typically motivated by their ability to encode context. Which aspects of context are captured by such representations? We introduce an approach to address this question using Representational Similarity Analysis (RSA). As case studies, we investigate the degree to which a verb embedding encodes the verb's subject, a pronoun embedding encodes the pronoun's antecedent, and a full-sentence representation encodes the sentence's head word (as determined by a dependency parse). In all cases, we show that BERT's contextualized embeddings reflect the linguistic dependency being studied, and that BERT encodes these dependencies to a greater degree than it encodes less linguistically-salient controls. These results demonstrate the ability of our approach to adjudicate between hypotheses about which aspects of context are encoded in representations of language.