© 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
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
PYTHIA-70M-DEDUPED · 0-MLP-SM · 29384 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
29384
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
URLs
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-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.0.hook_mlp_out
Hook Layer
0
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/0-mlp-sm/29384?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/0-mlp-sm/29384?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
230
+0.15
0.8%
7
+0.14
0.8%
446
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
509
+0.15
0.08
101
+0.14
0.06
175
+0.13
0.06
Negative Logits
kte
-1.70
pering
-1.63
clusion
-1.63
ien
-1.58
chter
-1.58
itions
-1.58
urai
-1.58
sure
-1.55
ondon
-1.53
igos
-1.50
POSITIVE LOGITS
ĨĴ
2.93
Ļª
2.37
¬
2.03
ı
1.77
§
1.70
¯
1.69
Ń
1.61
Ģ
1.61
ĥ
1.58
Ĵ
1.58
Act
ivations
Density 0.038%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
