# Emergence of a High-Dimensional Abstraction Phase in Language Transformers

arXiv: https://arxiv.org/abs/2405.15471 · HTML: https://mlsanity.com/paper/2405.15471/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 63 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [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)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [Intrinsic dimension of data representations in deep neural networks](https://mlsanity.com/paper/1905.12784/) (2019)
- [Estimating the intrinsic dimension of datasets by a minimal neighborhood information](https://mlsanity.com/paper/1803.06992/) (2018)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [The geometry of hidden representations of large transformer models](https://mlsanity.com/paper/2302.00294/) (2023)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)

## Built on by (most cited first, 30 of 56)

- [Layer by Layer: Uncovering Hidden Representations in Language Models](https://mlsanity.com/paper/2502.02013/) (2025)
- [Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts](https://mlsanity.com/paper/2509.26314/) (2025)
- [The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models](https://mlsanity.com/paper/2501.10573/) (2025)
- [Geometric Signatures of Compositionality Across a Language Model's Lifetime](https://mlsanity.com/paper/2410.01444/) (2024)
- [The representation landscape of few-shot learning and fine-tuning in large language models](https://mlsanity.com/paper/2409.03662/) (2024)
- [Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Models](https://mlsanity.com/paper/2409.05771/) (2024)
- [Persistent Topological Features in Large Language Models](https://mlsanity.com/paper/2410.11042/) (2024)
- [Layers at Similar Depths Generate Similar Activations Across LLM Architectures](https://mlsanity.com/paper/2504.08775/) (2025)
- [Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotion](https://mlsanity.com/paper/2510.04064/) (2025)
- [Representation Potentials of Foundation Models for Multimodal Alignment: A Survey](https://mlsanity.com/paper/2510.05184/) (2025)
- [Geometry of Decision Making in Language Models](https://mlsanity.com/paper/2511.20315/) (2025)
- [A quantitative analysis of semantic information in deep representations of text and images](https://mlsanity.com/paper/2505.17101/) (2025)
- [Differential syntactic and semantic encoding in LLMs](https://mlsanity.com/paper/2601.04765/) (2026)
- [Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models](https://mlsanity.com/paper/2506.02132/) (2025)
- [From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures](https://mlsanity.com/paper/2511.22150/) (2025)
- [Training the Untrainable: Introducing Inductive Bias via Representational Alignment](https://mlsanity.com/paper/2410.20035/) (2024)
- [The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models](https://mlsanity.com/paper/2412.06646/) (2024)
- [Prediction hubs are context-informed frequent tokens in LLMs](https://mlsanity.com/paper/2502.10201/) (2025)
- [LF2AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models](https://mlsanity.com/paper/2503.06211/) (2025)
- [TRACE for Tracking the Emergence of Semantic Representations in Transformers](https://mlsanity.com/paper/2505.17998/) (2025)
- [Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting](https://mlsanity.com/paper/2510.02480/) (2025)
- [Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations](https://mlsanity.com/paper/2601.03779/) (2026)
- [Disentangling Geometry, Performance, and Training in Language Models](https://mlsanity.com/paper/2602.20433/) (2026)
- [Uncovering the Latent Potential of Deep Intermediate Representations](https://mlsanity.com/paper/2605.23033/) (2026)
- [Automatic Layer Selection for Hallucination Detection](https://mlsanity.com/paper/2605.26366/) (2026)
- [Unsupervised detection of semantic correlations in big data](https://mlsanity.com/paper/2411.02126/) (2024)
- [The Generalization Ridge: Information Flow in Natural Language Generation](https://mlsanity.com/paper/2507.05387/) (2025)
- [Towards Understanding the Shape of Representations in Protein Language Models](https://mlsanity.com/paper/2509.24895/) (2025)
- [GenCtrl -- A Formal Controllability Toolkit for Generative Models](https://mlsanity.com/paper/2601.05637/) (2026)
- [Abstraction Induces the Brain Alignment of Language and Speech Models](https://mlsanity.com/paper/2602.04081/) (2026)

## Abstract (arXiv)

A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to its analysis, observing, across five pre-trained transformer-based LMs and three input datasets, a distinct phase characterized by high intrinsic dimensionality. During this phase, representations (1) correspond to the first full linguistic abstraction of the input; (2) are the first to viably transfer to downstream tasks; (3) predict each other across different LMs. Moreover, we find that an earlier onset of the phase strongly predicts better language modelling performance. In short, our results suggest that a central high-dimensionality phase underlies core linguistic processing in many common LM architectures.