© 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 · 0-MLP-SM · 27180 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
27180
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
the presence of the abbreviation "ph" in various contexts
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
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/27180?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/27180?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
164
+0.13
0.8%
502
+0.12
0.7%
300
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
300
+0.13
0.03
13
+0.12
0.03
58
+0.12
0.03
Negative Logits
·¸
-3.63
´
-3.60
»¿
-3.59
½
-3.50
Īĺ
-3.44
¼
-3.37
µ
-3.35
ĭ
-3.34
°
-3.30
±
-3.25
POSITIVE LOGITS
inx
1.76
works
1.75
pic
1.68
films
1.64
iko
1.52
sie
1.52
room
1.52
FW
1.51
aloud
1.50
fiction
1.50
Act
ivations
Density 2.341%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
