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
© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
2-MLP-SM
26191
Prev
Next
MODEL
2-mlp-sm
Source/SAE
INDEX
Go
Explanations
functional programming constructs and syntax in code
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__mlp-sm_processed/2-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.2.hook_mlp_out
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-mlp-sm/26191?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-mlp-sm/26191?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
298
+0.15
0.8%
106
+0.10
0.6%
153
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
208
+0.15
0.03
29
+0.10
0.02
465
+0.10
0.05
Negative Logits
Ĥ
-2.58
¿
-2.40
Ŀ
-2.36
IJ
-2.35
ª
-2.32
Īĺ
-2.19
®
-2.19
ľĵ
-2.17
ı
-2.14
Ģ
-2.14
POSITIVE LOGITS
isans
1.72
itals
1.67
ault
1.66
ête
1.61
iele
1.53
stit
1.48
taire
1.47
elles
1.47
rooms
1.45
LEY
1.45
Act
ivations
Density 0.351%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
