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
11463
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
words or abbreviations that indicate organization names
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__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/11463?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/11463?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
406
+0.15
0.8%
410
+0.12
0.6%
420
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
420
+0.15
0.03
360
+0.12
0.03
241
+0.11
0.03
Negative Logits
minded
-1.60
trial
-1.56
speedy
-1.47
iors
-1.46
legend
-1.46
fected
-1.43
way
-1.41
liar
-1.38
i
-1.35
iologic
-1.34
POSITIVE LOGITS
¥
3.34
ı
3.27
¤
3.14
·
3.09
Ļª
3.02
ī
3.00
IJ
3.00
ĥ½
2.93
ĭ
2.87
¯
2.84
Act
ivations
Density 0.122%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
