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
26204
Prev
Next
MODEL
2-mlp-sm
Source/SAE
INDEX
Go
Explanations
names of notable individuals, particularly those associated with the arts and entertainment
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/26204?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/26204?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
23
+0.16
0.9%
84
+0.12
0.7%
185
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
232
+0.16
0.09
151
+0.12
0.09
125
+0.11
0.09
Negative Logits
ÃŃa
-1.67
ERTYPE
-1.54
legate
-1.52
phia
-1.45
anmar
-1.44
iei
-1.44
asone
-1.41
ignon
-1.40
enue
-1.38
fony
-1.38
POSITIVE LOGITS
Ĺ
2.54
»
2.49
¥
2.28
¿
2.20
«
2.20
ļ
2.17
ľ
2.15
ª
2.15
°
2.13
¸
2.13
Act
ivations
Density 0.721%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
