Cross-Layer Transcoders decompose ViT activations into sparse, depth-aware layer contributions that maintain zero-shot accuracy and enable faithful attribution of the final representation.
Sparse autoencoders reveal selective remapping of visual concepts during adaptation
6 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
6
Pith papers citing it
1
external citations · external index
fields
cs.CV 6representative citing papers
The paper proposes information scope as a new interpretability axis for SAE features in CLIP and introduces the Contextual Dependency Score to separate local from global scope features, showing they influence model predictions differently.
A new SAE-based framework extracts visual, textual, and multimodal concepts from VLMs and reports up to 45% better visual concept quality on a VQA dataset while identifying multimodal concepts.
GeoSAE extracts a compact, interpretable feature set from frozen brain MRI foundation models that predicts MCI-to-AD conversion (AUC 0.746) with age-deconfounded annotations and replicates across cohorts.
LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
A sparse-autoencoder-based, label-free steering update to CLIP image embeddings improves zero-shot classification on nine datasets and comes with an FVU-based reliability gate.
citing papers explorer
-
Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
Cross-Layer Transcoders decompose ViT activations into sparse, depth-aware layer contributions that maintain zero-shot accuracy and enable faithful attribution of the final representation.
-
Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
The paper proposes information scope as a new interpretability axis for SAE features in CLIP and introduces the Contextual Dependency Score to separate local from global scope features, showing they influence model predictions differently.
-
Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders
A new SAE-based framework extracts visual, textual, and multimodal concepts from VLMs and reports up to 45% better visual concept quality on a VQA dataset while identifying multimodal concepts.
-
GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
GeoSAE extracts a compact, interpretable feature set from frozen brain MRI foundation models that predicts MCI-to-AD conversion (AUC 0.746) with age-deconfounded annotations and replicates across cohorts.
-
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
-
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
A sparse-autoencoder-based, label-free steering update to CLIP image embeddings improves zero-shot classification on nine datasets and comes with an FVU-based reliability gate.