© 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 · 2-MLP-SM · 24164 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
2-MLP-SM
24164
Prev
Next
MODEL
2-mlp-sm
Source/SAE
INDEX
Go
Explanations
terms related to heart health and cardiovascular issues
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/24164?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/24164?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
156
+0.22
1.2%
23
+0.20
1.1%
511
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
23
+0.22
0.01
511
+0.20
0.01
212
+0.14
0.02
Negative Logits
º
-2.35
«
-2.07
Ł
-2.04
¥
-2.03
ŀ
-2.02
į
-2.02
Ľ
-2.00
¾
-1.88
Ŀ
-1.87
ļ
-1.79
POSITIVE LOGITS
itrile
1.53
indicated
1.42
Edison
1.41
ismatic
1.36
ocrates
1.33
OPE
1.33
asis
1.32
ip
1.31
:--
1.29
"*
1.28
Act
ivations
Density 0.217%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
