Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Under Peer Review · Attention SAE Research Paper
GPT2-Small
Attention Out
10-ATT-KK
14709
Prev
Next
MODEL
10-att-kk
Source/SAE
INDEX
Go
Explanations
activities and transactions related to media and reporting, especially in a political or sports context
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 10-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
24,576
Data Type
float32
Hook Name
blocks.10.attn.hook_z
Hook Layer
10
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/10-att-kk/14709?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/10-att-kk/14709?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.05
1:
0.05
2:
0.10
3:
0.09
4:
0.07
5:
0.04
6:
0.03
7:
0.05
8:
0.03
9:
0.36
10:
0.04
11:
0.04
Negative Logits
�
-3.90
�
-3.02
†
-2.69
�
-2.53
�
-2.49
kaya
-2.49
%%
-2.49
�
-2.45
�
-2.42
¨
-2.42
POSITIVE LOGITS
his
7.06
his
7.04
His
6.99
himself
6.59
His
5.85
He
5.84
he
5.83
HIS
5.45
him
5.33
He
5.21
Act
ivations
Density 3.475%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Breaks
Hide Breaks
No Known Activations
