Cover Image

Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Prasad, Aaditya Vikram, Watts, Connor, Merullo, Jack, Gala, Dhruvil, Lewis, Owen, McGrath, Thomas, Lubana, Ekdeep Singh
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
by: Bigelow, Eric, et al.
Published: (2026)

The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors
by: Sarfati, Raphaël, et al.
Published: (2026)

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

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
by: Ramesh, Rahul, 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)

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

From Memorization to Reasoning in the Spectrum of Loss Curvature
by: Merullo, Jack, et al.
Published: (2025)

Binomial confidence intervals for rare events: importance of defining margin of error relative to magnitude of proportion
by: McGrath, Owen, et al.
Published: (2021)

A General Simulation-Based Optimisation Framework for Multipoint Constant-Stress Accelerated Life Tests
by: McGrath, Owen, et al.
Published: (2025)

A General Simulation‐Based Optimisation Framework for Multipoint Constant‐Stress Accelerated Life Tests
by: Owen McGrath, et al.
Published: (2025)

Supporting Data: Linking Geodetically Resolved Uplift to Long-Term Orogenic Exhumation in the Southern Alps, New Zealand
by: McGrath, Jack, et al.
Published: (2025)

Correlating the Subjects of Books Taken Out of and Books Used Within an Open-Stack Library
by: McGrath, William E.
Published: (1971)

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

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)

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

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

A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
by: Lubana, Ekdeep Singh, et al.
Published: (2024)

Competition Dynamics Shape Algorithmic Phases of In-Context Learning
by: Park, Core Francisco, et al.
Published: (2024)

Circuit Component Reuse Across Tasks in Transformer Language Models
by: Merullo, Jack, et al.
Published: (2023)

Raja Yudhisthira
by: McGrath, Kevin
Published: (2024)

Dimension Polynomials for Affine Partial Difference Algebraic Groups
by: McGrath, Orla
Published: (2025)

Don Quixote and Catholicism
by: McGrath, Michael
Published: (2024)

Using the Australian Dietary Guidelines 2&5 education message in supermarket shopping trolleys to nudge shoppers to purchase more fruit and vegetables: A feasibility study using an intervention design
by: Greg McGrath
Published: (2024)

High School Teachers' Perceptions of Student Information Literacy Competency Skills, Levels of Teacher Librarian Collaboration, and Teacher Experiences of Collaboration with School Librarians in the Mountain West: A Mixed Methods Study
by: Lance McGrath
Published: (2024)

We have positive epistemic duties
by: Matthew McGrath
Published: (2025)

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

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)

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

Response: The Problem of Shifting Scientific Paradigms: On Avoiding Premature Closure of Questions in Science and Religion
by: Alister E. McGrath
Published: (2025)

Intracellular accumulation of Polyphosphate by the Yeast Candida humicola G-1 in response to acid pH. / John W. McGrath
by: McGrath, John W
Published: (2000)

Sensor Technologies Healthcare, Wellness and Environmental Applications.
by: Michael J. McGrath.

Comparisons of the 1995 and 1998 coral bleaching events on the patch reefs of San Salvador Island, Bahamas
by: Thomas A. McGrath
Published: (2003)

Admission Systems and Student Mobility: A Proposal for an EU-Wide Registry for University Admission
by: Cecile Hoareau McGrath
Published: (2016)

Relationship between Hard/Soft, Pure/Applied, and Life/Nonlife Disciplines and Subject Book Use in a University Library.
by: McGrath, William E.
Published: (1975)

Completing the BSN Off-Campus.
by: McGrath, Barbara Jo
Published: (1984)