JE
Joshua Engels
cs.LGcs.AIcs.CLclusteringcs.CYlarge language modelsmechanistic interpretabilityneural networksq-bio.NCsparse coding
On Valency
published · living versionsW_cr3nzw48·v1 · currentpublished
Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL
with Aria Wong, Neel Nanda
1 version
Preprints & journals
12 papers in the corpus · 2024–2026How Transparent is DiffusionGemma?2606.20560v2 · Joshua Engels, Callum McDougall, Bilal Chughtai et al.2026 · 0 citationsarXiv
Training on Documents About Monitoring Leads to CoT Obfuscation2605.15257v1 · Reilly Haskins, Bilal Chughtai, Joshua Engels2026 · 0 citationsarXiv
Building Production-Ready Probes For Gemini2601.11516v4 · J'anos Kram'ar, Joshua Engels, Zheng Wang et al.2026 · 0 citationsarXiv
Simple Mechanistic Explanations for Out-Of-Context Reasoning2507.08218v2 · Atticus Wang, Joshua Engels, Oliver Clive-Griffin et al.2025 · 0 citationsarXiv
Dense SAE Latents Are Features, Not Bugs2506.15679v2 · Xiaoqing Sun, Alessandro Stolfo, Joshua Engels et al.2025 · 0 citationsarXiv
Scaling Laws For Scalable Oversight2504.18530v3 · Joshua Engels, David D. Baek, Subhash Kantamneni et al.2025 · 5 citationsNeurIPS 2025 (Spotlight)
The Geometry of Concepts: Sparse Autoencoder Feature Structure.40282579 · Li, Yuxiao, Michaud, Eric J, Baek, David D et al.2026 · 14 citationsEntropy (Basel, Switzerland). 2025;27(4)
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing2502.16681v1 · Subhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan et al.2025 · 0 citationsarXiv
Low-Rank Adapting Models for Sparse Autoencoders2501.19406v2 · Matthew Chen, Joshua Engels, Max Tegmark2025 · 1 citationarXiv
Decomposing The Dark Matter of Sparse Autoencoders2410.14670v2 · Joshua Engels, Logan Riggs, Max Tegmark2024 · 1 citationarXiv
Efficient Dictionary Learning with Switch Sparse Autoencoders2410.08201v2 · Anish Mudide, Joshua Engels, Eric J. Michaud et al.2024 · 0 citationsarXiv
Not All Language Model Features Are One-Dimensionally Linear2405.14860v3 · Joshua Engels, Eric J. Michaud, Isaac Liao et al.2024 · 4 citationsarXiv
Career total: 12 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.