Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
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
29045
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
references to other individuals or groups in a collective context
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/pythia-70m-deduped/2-res-sm/29045?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/2-res-sm/29045?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
365
+0.17
1.0%
130
+0.15
0.8%
247
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
365
+0.17
0.02
239
+0.15
0.03
130
+0.14
0.03
Negative Logits
©
-2.98
¯
-2.80
¬
-2.80
ĥ½
-2.76
¤
-2.74
ŀ
-2.72
²
-2.64
«
-2.63
ģ
-2.63
ĻĤ
-2.52
POSITIVE LOGITS
pace
2.07
hit
1.82
hu
1.72
ick
1.72
iscus
1.67
cript
1.65
lash
1.64
hip
1.61
uit
1.61
creen
1.58
Act
ivations
Density 0.153%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
