Cover Image

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Jiuding, Huang, Jing, Baskaran, Sidharth, D'Oosterlinck, Karel, Potts, Christopher, Sklar, Michael, Geiger, Atticus
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HyperSteer: Activation Steering at Scale with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

Updating CLIP to Prefer Descriptions Over Captions
by: Zur, Amir, et al.
Published: (2024)

In-Context Learning for Extreme Multi-Label Classification
by: D'Oosterlinck, Karel, et al.
Published: (2024)

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
by: Huang, Jing, et al.
Published: (2024)

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
by: Wu, Zhengxuan, et al.
Published: (2023)

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
by: D'Oosterlinck, Karel, et al.
Published: (2024)

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
by: Wu, Zhengxuan, et al.
Published: (2024)

Constructing Interpretable Features from Compositional Neuron Groups
by: Shafran, Or, et al.
Published: (2025)

Enhancing Automated Interpretability with Output-Centric Feature Descriptions
by: Gur-Arieh, Yoav, et al.
Published: (2025)

ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning
by: She, Jingyuan Selena, et al.
Published: (2023)

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
by: Wu, Zhengxuan, et al.
Published: (2024)

Composing Policy Gradients and Prompt Optimization for Language Model Programs
by: Ziems, Noah, et al.
Published: (2025)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
by: Wu, Zhengxuan, et al.
Published: (2025)

ReFT: Representation Finetuning for Language Models
by: Wu, Zhengxuan, et al.
Published: (2024)

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
by: Geiger, Atticus, et al.
Published: (2023)

Hyper-CL: Conditioning Sentence Representations with Hypernetworks
by: Yoo, Young Hyun, et al.
Published: (2024)

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
by: Gupta, Akshat, et al.
Published: (2024)

MIB: A Mechanistic Interpretability Benchmark
by: Mueller, Aaron, et al.
Published: (2025)

Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
by: Geiger, Atticus, et al.
Published: (2023)

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
by: Gur-Arieh, Yoav, et al.
Published: (2025)

How Causal Abstraction Underpins Computational Explanation
by: Geiger, Atticus, et al.
Published: (2025)

How Do Transformers Learn Variable Binding in Symbolic Programs?
by: Wu, Yiwei, et al.
Published: (2025)

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
by: Csordás, Róbert, et al.
Published: (2024)

FLRT: Fluent Student-Teacher Redteaming
by: Thompson, T. Ben, et al.
Published: (2024)

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

HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks
by: Zeng, Yiming, et al.
Published: (2025)

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
by: Wu, Zhengxuan, et al.
Published: (2023)

HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
by: Li, Yingting, et al.
Published: (2024)

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
by: Puyin, Li, et al.
Published: (2026)

Simple Mechanistic Explanations for Out-Of-Context Reasoning
by: Wang, Atticus, et al.
Published: (2025)

From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
by: Shafran, Or, et al.
Published: (2026)

Activation Steering via Generative Causal Mediation
by: Sankaranarayanan, Aruna, et al.
Published: (2026)

HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling
by: Ortiz-Barajas, Jesus-German, et al.
Published: (2024)

Fluent dreaming for language models
by: Thompson, T. Ben, et al.
Published: (2024)

Demystifying Verbatim Memorization in Large Language Models
by: Huang, Jing, et al.
Published: (2024)

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance
by: Zhang, Hao, et al.
Published: (2025)

Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
by: Trott, Sean
Published: (2025)

Tracking Equivalent Mechanistic Interpretations Across Neural Networks
by: Sun, Alan, et al.
Published: (2026)

VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback
by: Zhang, Guoxi, et al.
Published: (2024)

Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability
by: Chhabra, Vishnu Kabir, et al.
Published: (2025)