© 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 · 0-MLP-SM · 29553 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
29553
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
instances of the word "this."
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/29553?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/29553?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
100
+0.11
0.6%
169
+0.11
0.6%
285
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
402
+0.11
0.16
26
+0.11
0.14
199
+0.10
0.14
Negative Logits
Ģ
-3.32
©
-3.25
§
-3.15
¬
-3.13
ŀ
-2.99
Ļ
-2.98
Ī
-2.90
ĨĴ
-2.84
Ļª
-2.79
¿½
-2.75
POSITIVE LOGITS
áĢº
1.56
áĢ¯
1.51
ા
1.48
(&
1.40
|_
1.39
bbe
1.38
(__
1.35
$)
1.35
anmar
1.32
ied
1.32
Act
ivations
Density 0.384%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
