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
0-MLP-SM
27354
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
mentions of "points" in various contexts
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__mlp-sm_processed/0-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.0.hook_mlp_out
Hook Layer
0
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/0-mlp-sm/27354?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27354?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
156
+0.15
0.9%
376
+0.14
0.8%
255
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
255
+0.15
0.01
286
+0.14
0.01
260
+0.12
0.01
Negative Logits
ĥ½
-3.20
§
-2.81
Ĥ
-2.67
©
-2.63
¿½
-2.61
Ĥ¬
-2.59
¦
-2.56
ľ
-2.52
·
-2.52
ĥ
-2.42
POSITIVE LOGITS
heet
2.33
ional
1.99
erve
1.97
ionale
1.88
hips
1.85
heets
1.85
ior
1.85
agem
1.83
avia
1.80
etable
1.79
Act
ivations
Density 0.013%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
