Pith. sign in

REVIEW 5 cited by

The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.03662 v3 pith:RMB7FBFY submitted 2024-06-06 cs.LG

Liv Gorton This is my paper · ORCID
classification cs.LG
keywords saesinceptionv1curvedetectorsfeaturesneuralneuronsautoencoders
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early vision layers of InceptionV1, a well-studied convolutional neural network, with a focus on curve detectors. Our results demonstrate that SAEs can uncover new interpretable features not apparent from examining individual neurons, including additional curve detectors that fill in previous gaps. We also find that SAEs can decompose some polysemantic neurons into more monosemantic constituent features. These findings suggest SAEs are a valuable tool for understanding InceptionV1, and convolutional neural networks more generally.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A supervised sparse autoencoder binds each concept to a single neuron, letting Stable Diffusion erase a concept by steering one latent.

  2. Relevance-driven Input Dropout: an Explanation-guided Regularization Technique

    cs.LG 2025-05 conditional novelty 6.0 of 10

    RelDrop, which occludes the most attribution-relevant input regions during training, improves generalization and occlusion robustness for image and point cloud classification.

  3. Evaluating SAE interpretability without explanations

    cs.LG 2025-07 conditional novelty 5.0 of 10

    SAE latent interpretability can be scored directly from activation examples via intruder detection and embedding clustering, with LLM scores correlating strongly with human scores.

  4. Interpreting and Steering Protein Language Models through Sparse Autoencoders

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Amplifying specific sparse-autoencoder latents inside ESM-2 biases sequence generation toward zinc finger motifs, with a low success rate and incomplete statistical validation.

  5. A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models

    cs.CL 2026-01 reject novelty 4.0 of 10

    Using a sparse autoencoder bottleneck before attribution lowers reported RIS/ROS instability scores for a ModernBERT Alzheimer's classifier, but the improvement is measured with the optimizer's own training objective.

Pith tools