© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Models
Pythia-70M-Deduped
pythia-70m-deduped
EleutherAI
Jump to Source/SAE
0-att-sm
Source/SAE
Go
Jump to Feature
0-att-sm
Source/SAE
INDEX
Go
Releases
Sparse Autoencoders for Pythia-70M-Deduped
April 2024
Under Peer Review
p70d-sm
Attention Visualizer
HeadVis
(Luger, Kamath et al.)
Find Head By Metric
Metric & Number of Heads
Induction Score
Prev Token Score
Attention Entropy
Self Attention
Top 8
Click head to select
Layer 1
Head 0
Head 2
Head 7
Layer 2
Head 5
Layer 3
Head 1
Head 3
Layer 4
Head 1
Head 3
Select Head Manually
Layer
0
1
2
3
4
5
Head Index
0
1
2
3
4
5
6
7
Search Explanations
All
By Release
By Model
By Sources
MODEL
Show Dashboards
Hide Dashboards
Search via Inference
?
Inference is not currently not enabled for this model.
Request
Browse
MODEL
Attention Out
LAYER
Features in
P70M-D
@
0-att-sm
Hover over a feature on the left to preview its details.
Click a feature to lock it and interact with it.