Calibrated concept profiles: making the reading of a model's neurons a measurement
cs.CL, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
- Certified Circuits: Stability Guarantees for Mechanistic Circuits
- Network Dissection: Quantifying Interpretability of Deep Visual Representations
- Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Knowledge Neurons in Pretrained Transformers
- Toy Models of Superposition
- Transformer Feed-Forward Layers Are Key-Value Memories
- Universal Neurons in GPT2 Language Models
- OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
- How Programming Concepts and Neurons Are Shared in Code Language Models
- Visualizing and Understanding Recurrent Networks
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
- Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
- Redundancy and Concept Analysis for Code-trained Language Models
- Analyzing the Generalization and Reliability of Steering Vectors
- Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
- Neurons in Large Language Models: Dead, N-gram, Positional
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data