Cover Image

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fel, Thomas, Wang, Binxu, Lepori, Michael A., Kowal, Matthew, Lee, Andrew, Balestriero, Randall, Joseph, Sonia, Lubana, Ekdeep S., Konkle, Talia, Ba, Demba, Wattenberg, Martin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
by: Fel, Thomas, et al.
Published: (2025)

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
by: Hindupur, Sai Sumedh R., et al.
Published: (2025)

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
by: Costa, Valérie, et al.
Published: (2025)

Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit
by: Costa, Valérie, et al.
Published: (2025)

Interpreting Physics in Video World Models
by: Joseph, Sonia, et al.
Published: (2026)

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
by: Bohacek, Matyas, et al.
Published: (2025)

Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models
by: Doshi, Fenil R., et al.
Published: (2025)

Bi-Orthogonal Factor Decomposition for Vision Transformers
by: Doshi, Fenil R., et al.
Published: (2026)

Do Sparse Autoencoders Capture Concept Manifolds?
by: Bhalla, Usha, et al.
Published: (2026)

Feature Accentuation: Revealing 'What' Features Respond to in Natural Images
by: Hamblin, Chris, et al.
Published: (2024)

Priors in Time: Missing Inductive Biases for Language Model Interpretability
by: Lubana, Ekdeep Singh, et al.
Published: (2025)

Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks
by: Patel, Niket, et al.
Published: (2025)

Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
by: Park, Core Francisco, et al.
Published: (2024)

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
by: Thasarathan, Harrish, et al.
Published: (2025)

Block-Recurrent Dynamics in Vision Transformers
by: Jacobs, Mozes, et al.
Published: (2025)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
by: Mueller, Aaron, et al.
Published: (2025)

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
by: Okawa, Maya, et al.
Published: (2023)

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
by: Wurgaft, Daniel, et al.
Published: (2026)

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
by: Jaipersaud, Brandon, et al.
Published: (2025)

Abrupt Learning in Transformers: A Case Study on Matrix Completion
by: Gopalani, Pulkit, et al.
Published: (2024)

ICLR: In-Context Learning of Representations
by: Park, Core Francisco, et al.
Published: (2024)

On the Geometry of Deep Learning
by: Balestriero, Randall, et al.
Published: (2024)

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
by: Balestriero, Randall, et al.
Published: (2023)

Swing-by Dynamics in Concept Learning and Compositional Generalization
by: Yang, Yongyi, et al.
Published: (2024)

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
by: Ramesh, Rahul, et al.
Published: (2023)

Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies
by: Grosso, Gaia, et al.
Published: (2025)

The Geometry of Self-Verification in a Task-Specific Reasoning Model
by: Lee, Andrew, et al.
Published: (2025)

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
by: Feucht, Sheridan, et al.
Published: (2026)

Clustering Inductive Biases with Unrolled Networks
by: Huml, Jonathan, et al.
Published: (2023)

Implicit Generative Modeling by Kernel Similarity Matching
by: Choudhary, Shubham, et al.
Published: (2025)

Weighed l1 on the simplex: Compressive sensing meets locality
by: Tasissa, Abiy, et al.
Published: (2021)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
by: Zur, Amir, et al.
Published: (2025)

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
by: Pres, Itamar, et al.
Published: (2024)

Analyzing (In)Abilities of SAEs via Formal Languages
by: Menon, Abhinav, et al.
Published: (2024)

No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
by: Cai, Daniel, et al.
Published: (2025)

Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting
by: Dronen, Nicholas, et al.
Published: (2025)

SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth
by: Masi, Nick, et al.
Published: (2025)

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
by: Huang, Hai, et al.
Published: (2024)

Understanding Inhibition Through Maximally Tense Images
by: Hamblin, Chris, et al.
Published: (2024)

FOVI: A biologically-inspired foveated interface for deep vision models
by: Blauch, Nicholas M., et al.
Published: (2026)