Interpretability

Feeds to Scour
SubscribedAll
Scoured 69 posts in 6.9 ms

Mechanistic Interpretability: The Key to Trusting Agentic AI

馃AgentContent type: Discussion
bradenkelley.com

Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects

馃攳RAGContent type: Academic
arxiv.org

rentruewang/inversql: Create SQL that match your selection (with explainable AI), not the other way around

馃攳RAGContent type: Code
github.comHacker News

What shapes your power bill? Explainable AI outlines forecasts behind grid and price decisions

馃捑Memory Systems
techxplore.com

How Does XAI Actually Work? A Look at SHAP and LIME in Cybersecurity

馃幆AlignmentContent type: Blog
medium.com

Building MalTrace: A Behavioral Malware Analysis Pipeline with Explainable AI

馃Cognitive Neurosciens for AIContent type: Blog
medium.com

Compositional and interpretable representation of histology using AI foundation models and sparse autoencoders

馃帹Multimodal AIContent type: Academic
biorxiv.org

AI Predicts Brain Tumor Molecular Subtypes in Twelve Minutes

馃Neuroscience
neurosciencenews.com

Playing with Vision Embeddings

馃帹Multimodal AI

A Practical Guide to Assessing Agentic AI Companies for Enterprise Needs

馃Agent
netnewsledger.com

[Paper] Dictionary Learning Identifiability for Understanding SAEs

馃捑Memory Systems
lesswrong.com

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

馃捑Memory SystemsContent type: Academic
arxiv.org
Less-relevant results

Is the Space Pope Reptilian?

馃幆AlignmentContent type: News
tearsinrain.aiHacker News

DataXflowGen for GenAI-driven model generation

馃帹Multimodal AIContent type: Academic
nature.com

Anish-185/Production-Line-Performance-Checker

馃幆AlignmentContent type: Code
github.comr/coding

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

馃帹Multimodal AIContent type: Academic
arxiv.org

BioByte 162: The Hype of Virtual Cells, ESMC's AlphaFold3-Like Performance, and the Prediction of Antibody Non-Specificity

馃攳RAGContent type: Blog

Why Digital Identity Fraud Is Becoming a Bigger Threat to Financial Services

馃幆Alignment

Trajectory Geometry of Transformer Representations Across Layers

馃NeuroscienceContent type: Academic
arxiv.org

Coelho Mollo and Milli猫re: The Vector Grounding Problem

馃Embodied AI
philosophyofbrains.com

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