# Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures

arXiv: https://arxiv.org/abs/2410.06672 · HTML: https://mlsanity.com/paper/2410.06672/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)
- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (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)
- [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)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [Transformer Quality in Linear Time](https://mlsanity.com/paper/2202.10447/) (2022)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations](https://mlsanity.com/paper/2302.03025/) (2023)
- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [Identifying and Controlling Important Neurons in Neural Machine Translation](https://mlsanity.com/paper/1811.01157/) (2018)
- [Universal Neurons in GPT2 Language Models](https://mlsanity.com/paper/2401.12181/) (2024)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation](https://mlsanity.com/paper/1810.11750/) (2018)
- [Geometry Score: A Method For Comparing Generative Adversarial Networks](https://mlsanity.com/paper/1802.02664/) (2018)
- [Locating and Editing Factual Associations in Mamba](https://mlsanity.com/paper/2404.03646/) (2024)

## Built on by (most cited first, 30 of 31)

- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [Analyze Feature Flow to Enhance Interpretation and Steering in Language Models](https://mlsanity.com/paper/2502.03032/) (2025)
- [Layers at Similar Depths Generate Similar Activations Across LLM Architectures](https://mlsanity.com/paper/2504.08775/) (2025)
- [Representation Potentials of Foundation Models for Multimodal Alignment: A Survey](https://mlsanity.com/paper/2510.05184/) (2025)
- [Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition](https://mlsanity.com/paper/2504.20938/) (2025)
- [Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning](https://mlsanity.com/paper/2507.10624/) (2025)
- [Evolution of Concepts in Language Model Pre-Training](https://mlsanity.com/paper/2509.17196/) (2025)
- [Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning](https://mlsanity.com/paper/2508.16929/) (2025)
- [How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders](https://mlsanity.com/paper/2503.06394/) (2025)
- [Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel](https://mlsanity.com/paper/2601.10266/) (2026)
- [Superposition disentanglement of neural representations reveals hidden alignment](https://mlsanity.com/paper/2510.03186/) (2025)
- [The Indra Representation Hypothesis for Multimodal Alignment](https://mlsanity.com/paper/2604.04496/) (2026)
- [Model Alignment Search](https://mlsanity.com/paper/2501.06164/) (2025)
- [Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks](https://mlsanity.com/paper/2602.22719/) (2026)
- [Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer](https://mlsanity.com/paper/2604.24302/) (2026)
- [Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study](https://mlsanity.com/paper/2608.05164/) (2026)
- [Explaining How Visual, Textual and Multimodal Encoders Share Concepts](https://mlsanity.com/paper/2507.18512/) (2025)
- [WriteSAE: Sparse Autoencoders for Recurrent State](https://mlsanity.com/paper/2605.12770/) (2026)
- [Interpretability Transfer from Language to Vision via Sparse Autoencoders](https://mlsanity.com/paper/2605.24946/) (2026)
- [Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders](https://mlsanity.com/paper/2606.12138/) (2026)
- [Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact](https://mlsanity.com/paper/2508.00903/) (2025)
- [The Deleuzian Representation Hypothesis](https://mlsanity.com/paper/2512.19734/) (2025)
- [Refit the Probe: Single-Direction Ablation Is Not a Necessity Test](https://mlsanity.com/paper/2606.00926/) (2026)
- [Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures](https://mlsanity.com/paper/2606.16897/) (2026)
- [What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations](https://mlsanity.com/paper/2607.21491/) (2026)
- [Mapping and Measuring the Behavioral Evolution of Large Language Models](https://mlsanity.com/paper/2608.11027/) (2026)
- [SharedSAE: One Feature Dictionary Across Language Models](https://mlsanity.com/paper/2609.04344/) (2026)
- [Locating and Steering Refusal Beyond Attention](https://mlsanity.com/paper/2609.04721/) (2026)
- [Global Divergence, Local Convergence: Representation Geometry in SSMs and Transformers](https://mlsanity.com/paper/2609.08692/) (2026)
- [Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders](https://mlsanity.com/paper/2609.24440/) (2026)

## Abstract (arXiv)

The hypothesis of Universality in interpretability suggests that different neural networks may converge to implement similar algorithms on similar tasks. In this work, we investigate two mainstream architectures for language modeling, namely Transformers and Mambas, to explore the extent of their mechanistic similarity. We propose to use Sparse Autoencoders (SAEs) to isolate interpretable features from these models and show that most features are similar in these two models. We also validate the correlation between feature similarity and Universality. We then delve into the circuit-level analysis of Mamba models and find that the induction circuits in Mamba are structurally analogous to those in Transformers. We also identify a nuanced difference we call Off-by-One motif: The information of one token is written into the SSM state in its next position. Whilst interaction between tokens in Transformers does not exhibit such trend.