© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
MAY 26
Assistant Axis
JAN 26
Circuit Tracer
APR 26
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
Docs
Community
Blog
Privacy & Terms
Contact
Sign In
PYTHIA-70M-DEDUPED · 1-RES-SM · 23840 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
1-RES-SM
23840
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
references to specific events or details related to a narrative or report
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-haiku-5-5
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.hook_resid_post
Hook Layer
1
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/1-res-sm/23840?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/1-res-sm/23840?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Neuron Alignment
Index
Value
% of L₁
156
+0.22
1.3%
23
+0.19
1.1%
72
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
111
+0.22
0.28
156
+0.19
0.23
271
+0.14
-0.04
Negative Logits
rico
-1.71
buntu
-1.52
usepackage
-1.49
еÑģк
-1.45
лÑĮ
-1.45
icago
-1.45
алÑĮ
-1.44
ане
-1.42
ÑģÑĤво
-1.42
ário
-1.41
POSITIVE LOGITS
ĻĤ
2.90
¿½
2.47
Ł
2.33
Ĺ
2.27
ĸ
2.26
¦
2.24
↵
2.22
2.22
2.22
2.22
Act
ivations
Density 5.484%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
