INTERVIEW: Polysemanticity w/ Dr. Darryl Wright

from Into AI Safety · host Jacob Haimes

Darryl and I discuss his background, how he became interested in machine learning, and a project we are currently working on investigating the penalization of polysemanticity during the training of neural networks.Check out a diagram of the decoder task used for our research!01:46 - Interview begins02:14 - Supernovae classification08:58 - Penalizing polysemanticity20:58 - Our "toy model"30:06 - Task description32:47 - Addressing hurdles39:20 - Lessons learnedLinks to all articles/papers which are mentioned throughout the episode can be found below, in order of their appearance.ZooniverseBlueDot ImpactAI Safety SupportZoom In: An Introduction to CircuitsMNIST dataset on PapersWithCodeClusterability in Neural NetworksCIFAR-10 datasetEffective Altruism GlobalCLIP (blog post)Long Term Future FundEngineering Monosemanticity in Toy Models

What this episode covers

Darryl and I discuss his background, how he became interested in machine learning, and a project we are currently working on investigating the penalization of polysemanticity during the training of neural networks. Check out a diagram of the decoder task used for our research! 01:46 - Interview begins02:14 - Supernovae classification08:58 - Penalizing polysemanticity20:58 - Our "toy model"30:06 - Task description32:47 - Addressing hurdles39:20 - Lessons learned Links to all articles/papers which are mentioned throughout the episode can be found below, in order of their appearance. Zooniverse BlueDot Impact AI Safety Support Zoom In: An Introduction to Circuits MNIST dataset on PapersWithCode Clusterability in Neural Networks CIFAR-10 dataset Effective Altruism Global CLIP (blog post) Long Term Future Fund Engineering Monosemanticity in Toy Models

NOW PLAYING

INTERVIEW: Polysemanticity w/ Dr. Darryl Wright

0:00 45:09

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

Why Live and Evergreen Models Both Fall Short

Feb 4, 2026 ·18m

Similar Podcasts

Destiny Architecture® Meditations Heather Larson Bring your mediation practice into the Valueverse. LIGHTS, CAMERA, SMILE! Creatives Club Media Lights, Camera, Smile, is a podcast for anyone with a dream to share something with the world, out of the overflow of themselves - be it their mind, their heart, their personalities, and much more. Each of us are alive in this moment in time, with an innate ability to have ideas and create various things to benefit both ourselves and the people around us for a reason, and here, you will find the encouragement, the inspiration, and the motivation to do just that. Hosted by Cicily, founder of Creatives Club, she dives into various topics surrounding creativity and business. Exploring entrepreneurship for creatives in a corporate reality, sharing tips and tricks in a media centered company, answering questions regarding what a creative actually is are just a few of the things discussed on this podcast. Be encouraged to create for yourself as Cicily gets vulnerable by pivoting the camera to herself for the first time.To submit questions for Cicily to answer, or have her address certain t Chewing the Fat with WorkForge WorkForge Bite-Sized Conversations for Building a Stronger Workforce Welcome to Chewing the Fat, a podcast delving deep into the world of food manufacturing. Dive into real conversations around critical topics like staffing, retention, onboarding, and career development in this essential industry. Subscribe now to gain insights from your peers, subject matter experts and more on the biggest issues facing food manufacturers today: -Hiring and retaining employees -Addressing the challenges of the Silver Tsunami -Improving time to productivity of new employees -Engaging employees from hire to retire And more... Tune in to Chewing the Fat, a WorkForge podcast, and join the conversation on how to build and sustain a resilient, high-performing workforce in food manufacturing. Darknet Discussions Darknet Discussions Welcome to "Darknet Discussions," the podcast that gets into the shadows of the internet to bring you the most intriguing, enlightening, and sometimes unsettling stories from the dark web. Hosted by seasoned darknet aficionados, each episode of "Darknet Discussions" explores the intricate dynamics of darknet markets, cybersecurity threats, and the digital underworld. Join us as we interview experts, discuss the latest trends in cybercrime, and shed light on the technologies that operate beneath the surface of everyday internet use. Also, we occasionally go off on a tangent about something completely unrelated.

Frequently Asked Questions

How long is this episode of Into AI Safety?

This episode is 45 minutes long.

When was this Into AI Safety episode published?

This episode was published on January 22, 2024.

What is this episode about?

Can I download this Into AI Safety episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.

URL copied to clipboard!