Interpretability

Feeds to Scour
SubscribedAll
Scoured 118 posts in 7.3 ms

princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how AI actually works

 🎲Procedural Generation  Content type: Code
github.com··Hacker News

Prediction: Quantum Computing Will Produce the Nasdaq's Best-Performing Stock of 2026

 🌐Distributed Systems  Content type: News
fool.com·

One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability

 🔬Mech Interp  Content type: Academic
arxiv.org·

Deutsch's Algorithm in Quantum Computing: The 4 Cases

 🔧Compilers
malcolmlow.com··DEV

Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers

 🔬Mech Interp  Content type: Academic
arxiv.org·

A first-in-class pulsatile FXR agonist for bile-acid-related liver diseases

 🐧Operating Systems  Content type: Academic
nature.com
·

Who Elected Anthropic?

 🛡️AI Safety  Content type: Blog

FoldSAE: Learning to Steer Protein Folding Through Sparse Representations

 🔬Mech Interp  Content type: Academic
arxiv.org·

Quantum ‘Fingerprints’ May Be Shaping Your Decisions—And Ultimately Your Free Will, Scientist Says

 🧘Meditation  Content type: News
popularmechanics.com·

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

 🔬Mech Interp  Content type: Academic
arxiv.org·

scMTG reconstructs single-cell temporal dynamics with Markov transition generators

 🛡️AI Safety  Content type: Academic
biorxiv.org·

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders

 🔬Mech Interp  Content type: Academic
arxiv.org·

Quantum Information as Everything

 🌐Distributed Systems  Content type: News  Content type: Blog

Physicists observe synchronized quantum dance of excitons and phonons

 🔬Mech Interp
phys.org·

Noise cancellation by superposition of channels and superactivation of quantum capacity: Experimental realization by NMR

 🌐Distributed Systems  Content type: Academic
arxiv.org·

SAE It Across Models: Explaining Features With Foreign NLA Verbalizers

 🔬Mech Interp
lesswrong.com·

Trajectory Geometry of Transformer Representations Across Layers

 🛡️AI Safety  Content type: Academic
arxiv.org·

Coelho Mollo and Millière: The Vector Grounding Problem

 🛡️AI Safety

Mechanistic Analysis of Alignment Algorithms in Language Models

 🔬Mech Interp  Content type: Academic
arxiv.org·

Roundup of links for 5 Jun.

 🗂️Personal Wikis
ideatrash.net·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help