Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
27288
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
instances of the word "position."
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/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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27288?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27288?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
115
+0.15
0.9%
31
+0.11
0.6%
172
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
31
+0.15
0.01
66
+0.11
0.01
465
+0.10
0.01
Negative Logits
ķ
-2.22
ĩ
-2.15
²
-2.14
ĥ½
-2.12
Ī
-2.08
»¿
-2.02
»
-1.98
½
-1.94
³
-1.93
?’
-1.91
POSITIVE LOGITS
ary
2.08
al
2.06
naire
2.00
erior
1.99
alent
1.98
istical
1.78
ist
1.77
ive
1.72
heses
1.71
ional
1.65
Act
ivations
Density 0.027%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
