© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
PYTHIA-70M-DEDUPED · 2-RES-SM · 29774 | Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
2-RES-SM
29774
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
phrases indicating curiosity or interest
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
How To Load
Prompts (Dashboard)
32,768 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
32,768
Data Type
torch.float32
Hook Name
blocks.2.hook_resid_post
Hook Layer
2
Architecture
standard
Context Size
128
Dataset
EleutherAI/the_pile_deduplicated
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/pythia-70m-deduped/2-res-sm/29774?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/2-res-sm/29774?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
365
+0.13
0.7%
505
+0.11
0.6%
221
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
38
+0.13
0.02
372
+0.11
0.01
365
+0.11
0.02
Negative Logits
ĻĤ
-2.82
Ĵ
-2.57
ĨĴ
-2.45
Īĺ
-2.37
¿½
-2.18
Ł
-2.16
į
-2.02
IJ
-2.00
ı
-2.00
Į
-1.89
POSITIVE LOGITS
edly
2.29
ively
2.02
iary
2.00
ality
1.98
alities
1.84
als
1.79
accru
1.70
ally
1.69
holder
1.61
area
1.60
Act
ivations
Density 0.164%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations