No article text was recorded for this version.
linear concept probing
Version 1 of 159 papers60 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors
- Blog: Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts
- Blog: CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation
- Blog: Concept Activation Vectors for Generating User-Defined 3D Shapes
- Blog: CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs
- Blog: Label-Efficient Group Robustness via Out-of-Distribution Concept Curation
- Blog: Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
- Blog: Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes
- Blog: Interpreting the Latent Space of GANs for Semantic Face Editing
- Blog: Interpreting Generative Adversarial Networks for Interactive Image Generation
- Blog: Concept Activation Vectors for Generating User-Defined 3D Shapes
- Blog: Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration
- Blog: Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection
- Blog: Learning Unsupervised Hierarchies of Audio Concepts
- Blog: Controlling Large Language Models Through Concept Activation Vectors
- Blog: Contrastive Corpus Attribution for Explaining Representations
- Blog: On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors
- Blog: Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
- Blog: InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs
- Blog: Inducing Symbolic Rules from Entity Embeddings using Auto-encoders
- Blog: Detecting High-Stakes Interactions with Activation Probes
- Blog: Hair Attribute Transfer via Deep Feature Fusion
- Blog: Exploring Representations and Interventions in Time Series Foundation Models
- Blog: Large Language Models can Become Strong Self-Detoxifiers
- Blog: Controllable Generative Modeling via Causal Reasoning
- Blog: Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
- Blog: Identifying Linear Relational Concepts in Large Language Models
- Blog: Learning Conceptual Spaces with Disentangled Facets
- Blog: Biais de genre encodés et exprimés dans les LLM : étude conjointe
- Blog: Scale-preserving automatic concept extraction (SPACE)
- Blog: Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation
- Blog: AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models
- Blog: Linear Probe Penalties Reduce LLM Sycophancy
- Blog: Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
- Blog: Death by a Thousand Directions: Exploring the Geometry of Harmfulness in LLMs through Subconcept Probing
- Blog: A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
- Blog: Towards a Deep Understanding of Multilingual End-to-End Speech Translation
- Blog: Feature Unlearning for Pre-trained GANs and VAEs
- Blog: The Geometry of Representational Failures in Vision Language Models
- Blog: Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- Blog: Analytical Methods for Interpretable Ultradense Word Embeddings
- Blog: ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesions
- Blog: Exploring Explainability in Video Action Recognition
- Blog: ChemSpacE: Interpretable and Interactive Chemical Space Exploration
- Blog: Concept Discovery for The Interpretation of Landscape Scenicness
- Blog: Image Generation with Global Photographic Aesthetic Based on Disentangled Generative Adversarial Network
- Blog: Advancing Interpretability of CLIP Representations with Concept Surrogate Model
- Blog: A Language Model’s Guide Through Latent Space
- Blog: Interpretable Basis Decomposition for Visual Explanation
- Blog: LatentVis: Investigating and Comparing Variational Auto-Encoders via Their Latent Space
- Blog: Net2Vec: Quantifying and Explaining How Concepts Are Encoded by Filters in Deep Neural Networks
- Blog: Meaningfully debugging model mistakes using conceptual counterfactual explanations
- Blog: Probing Political Ideology in Large Language Models: How Latent Political Representations Generalize Across Tasks
- Blog: Linearly Decoding Refused Knowledge in Aligned Language Models
- Blog: Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing
- Blog: How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
- Blog: How Does Controllability Emerge In Language Models During Pretraining?
- Blog: LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
- Blog: All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_linear_concept_probing_656fc001,
title = {linear concept probing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-concept-probing/rdr_656fc001f1f04da4adece6f70b572c13},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_linear_concept_probing_656fc001_v1,
title = {linear concept probing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-concept-probing/rdr_656fc001f1f04da4adece6f70b572c13/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}