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
2-MLP-SM
26272
Prev
Next
MODEL
2-mlp-sm
Source/SAE
INDEX
Go
Explanations
technical language and details related to scientific or engineering processes
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/pythia-70m-deduped/2-mlp-sm/26272?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/2-mlp-sm/26272?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
388
+0.13
0.8%
216
+0.13
0.7%
249
+0.11
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
168
+0.13
0.10
388
+0.13
0.04
363
+0.11
0.07
Negative Logits
documentclass
-1.74
$]{}
-1.68
rounds
-1.50
chers
-1.49
$$
-1.49
]}
-1.47
$
-1.46
awning
-1.46
pping
-1.40
indoors
-1.40
POSITIVE LOGITS
↵
2.37
2.37
↵
2.37
↵↵
2.37
2.37
↵↵
2.37
↵
2.37
č↵
2.37
↵
2.37
↵
2.37
Act
ivations
Density 3.075%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
