Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

arXiv:2609.29845 · cs.CL, cs.AI · Submitted 2026-09-24 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Fine-Tuning — 19× in this paper · explained in 5 episodes
• Transformer — 15× in this paper · explained in 2 episodes
• Distillation — 14× in this paper · explained in 2 episodes
• Embeddings — 13× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• Additivity — 3× in this paper · explained in 1 episode
• Fidelity — 3× in this paper · explained in 2 episodes
• Transformer Architecture — 3× in this paper · explained in 2 episodes
• Wasserstein Distance — 3× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Decode — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Kullback-Leibler (KL) Divergence — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Symmetry Breaking — 1× in this paper · explained in 3 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
• TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
• The Llama 3 Herd of Models
• OLMo: Accelerating the Science of Language Models
• MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition
• DataMUX: Data Multiplexing for Neural Networks
• The LAMBADA dataset: Word prediction requiring a broad discourse context
• The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
• Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
• Gemma 2: Improving Open Language Models at a Practical Size
• Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering