Academic Paper Visualization

Creator

Creator

Seonglae Cho

Created

Created

2024 Oct 25 17:2

Editor

Editor

Seonglae Cho

Edited

Edited

2025 Aug 27 23:11

Refs

Refs

Python Visualization

Data Visualization

Vector visualization

Academic Paper Template

Vibe research

Font is important, Font size should be big enough as the paper’s font size.

Put several aspect of insight with fixing some variable or visually fixed comparable size

3D graph is good but not necessary

vertical horizontal histogram for scatter plot is usefuls

https://arxiv.org/pdf/2505.24731

https://aclanthology.org/2025.acl-long.1141.pdf

https://transformer-circuits.pub/2021/framework/index.html

https://transformer-circuits.pub/2023/monosemantic-features

https://openreview.net/pdf?id=ugX4wvQcFt

https://arxiv.org/pdf/2402.17762

https://aclanthology.org/2025.acl-short.44.pdf

https://www.lesswrong.com/posts/k8bBx4HcTF9iyikma/sae-features-for-refusal-and-sycophancy-steering-vectors

https://arxiv.org/pdf/2501.12948 Not simple bar chart, add hatch or whatever

https://arxiv.org/pdf/2508.16153

https://arxiv.org/pdf/2505.17454

https://arxiv.org/pdf/2503.01822

https://aclanthology.org/2025.acl-long.1209.pdf

Insane visualization

color

fixed portion

comparable size

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Mechanistic interpretability seeks to understand neural networks by breaking them into components that are more easily understood than the whole. By understanding the function of each component, and how they interact, we hope to be able to reason about the behavior of the entire network. The first step in that program is to identify the correct components to analyze.

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

https://transformer-circuits.pub/2023/monosemantic-features

Interactive

Distill — Latest articles about machine learning

Articles about Machine Learning

https://distill.pub/

Distill — Latest articles about machine learning

Neural network

Tools-to-Design-or-Visualize-Architecture-of-Neural-Network

ashishpatel26 • Updated 2025 Aug 27 12:21

Effective complexity

Compressed Computation is (probably) not Computation in Superposition — LessWrong

This research was completed during the Mentorship for Alignment Research Students (MARS 2.0) Supervised Program for Alignment Research (SPAR spring 2…

Compressed Computation is (probably) not Computation in Superposition — LessWrong

https://www.lesswrong.com/posts/ZxFchCFJFcgysYsT9/compressed-computation-is-probably-not-computation-in

Compressed Computation is (probably) not Computation in Superposition — LessWrong

Backlinks

Academic Writing

Recommendations

/////