When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/Sai-Sumedh/comparison-geometry
Terminology
Sources
- Understanding intermediate layers using linear classifier probes
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
- How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
- Causal Abstractions of Neural Networks
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
- Localizing Model Behavior with Path Patching
- Language Models Represent Space and Time
- When Models Manipulate Manifolds: The Geometry of a Counting Task
- Explaining Attention with Program Synthesis
- Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
- Language Models Use Trigonometry to Do Addition
- Symmetry in language statistics shapes the geometry of model representations
- AtP*: An efficient and scalable method for localizing LLM behaviour to components
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
- Locating and Editing Factual Associations in GPT
- The Origins of Representation Manifolds in Large Language Models
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Attribution Patching Outperforms Automated Circuit Discovery
- Linear Representations of Sentiment in Large Language Models
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks