# Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models

arXiv: https://arxiv.org/abs/2408.11827 · HTML: https://mlsanity.com/paper/2408.11827/

## 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 22 of its 53 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [PMET: Precise Model Editing in a Transformer](https://mlsanity.com/paper/2308.08742/) (2023)
- [Information Flow Routes: Automatically Interpreting Language Models at Scale](https://mlsanity.com/paper/2403.00824/) (2024)
- [Definition Modeling: Learning to define word embeddings in natural language](https://mlsanity.com/paper/1612.00394/) (2016)
- [Explaining How Transformers Use Context to Build Predictions](https://mlsanity.com/paper/2305.12535/) (2023)
- [Analyzing Commonsense Emergence in Few-shot Knowledge Models](https://mlsanity.com/paper/2101.00297/) (2021)
- [BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling](https://mlsanity.com/paper/2207.06814/) (2022)
- [A Unified Understanding of Deep NLP Models for Text Classification](https://mlsanity.com/paper/2206.09355/) (2022)
- [Categorization of Semantic Roles for Dictionary Definitions](https://mlsanity.com/paper/1806.07711/) (2018)

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

- [ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning](https://mlsanity.com/paper/2510.18250/) (2025)
- [How Do Large Language Models Learn Concepts During Continual Pre-Training?](https://mlsanity.com/paper/2601.03570/) (2026)

## Abstract (arXiv)

Understanding how language models compose meaning from linguistic input remains a central problem in interpretability research. Mechanistic studies have attributed functional roles to core transformer components; however, these findings derive largely from factual retrieval settings. Whether the same mechanisms support textitconceptual interpretation, the compositional mapping from definitional expressions to abstract meaning, remains insufficiently characterised. We introduce textitDSRA (Definitional Semantic Role Analysis), a methodology that applies causal tracing within the reverse dictionary task and augments restoration traces with definitional semantic roles (DSRs) grounded in Argument Structure Theory. This linguistic overlay identifies which compositional functions (e.g., genus, differentia quality) are associated with high-recovery states, extending activation patching beyond token-level localisation. Applied to GPT-J-6B (English) and BERTIN GPT-J-6B (Spanish), the results show that MLP layers associate content-bearing tokens with high-specificity DSR categories in early layers, MHA layers distribute integration across middle-to-upper layers with concentration at the final token, and hidden states aggregate information in upper layers. Alignment between restored states and DSR categories indicates systematic correspondence between internal activations and definitional structure, with consistent localisation patterns across both languages.