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
29347
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
the word "still" and its contextual variations indicating continuity
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/29347?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/29347?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
9
+0.14
0.8%
241
+0.11
0.6%
338
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
206
+0.14
0.03
118
+0.11
0.04
28
+0.10
0.03
Negative Logits
ģ
-4.39
ĨĴ
-4.26
Ħ
-4.14
ħ
-4.04
ª
-4.01
ĸ
-3.94
ĩ
-3.84
-3.83
-3.83
-3.83
POSITIVE LOGITS
ness
1.64
birth
1.61
ders
1.50
GROUND
1.47
progress
1.45
born
1.44
pending
1.44
stock
1.42
strugg
1.41
haven
1.39
Act
ivations
Density 0.125%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
