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
Residuals
2-RES-SM
29331
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
words related to numbers and mathematical concepts
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__res-sm_processed/2-res-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_resid_post
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-res-sm/29331?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-res-sm/29331?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
410
+0.14
0.8%
203
+0.14
0.8%
111
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
38
+0.14
0.03
67
+0.14
0.03
7
+0.13
0.02
Negative Logits
àµį
-2.32
à±į
-2.28
à°¿
-2.06
rowser
-1.93
à±ģ
-1.83
à¯į
-1.76
ável
-1.71
ા
-1.71
able
-1.71
unsuccessful
-1.70
POSITIVE LOGITS
ĵ
4.85
IJ
4.80
·
4.77
ĻĤ
4.65
Ĭ
4.62
¤
4.60
©
4.55
į
4.52
¾
4.48
Ĵ
4.47
Act
ivations
Density 0.227%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
