Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Under Peer Review · Attention SAE Research Paper
GPT2-Small
Attention Out
2-ATT-KK
22271
Prev
Next
MODEL
2-att-kk
Source/SAE
INDEX
Go
Explanations
quotes that express opinions or statements about individuals or groups
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 @ 2-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.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.2.attn.hook_z
Hook Layer
2
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/2-att-kk/22271?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/2-att-kk/22271?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.20
1:
0.04
2:
0.06
3:
0.12
4:
0.03
5:
0.16
6:
0.05
7:
0.04
8:
0.04
9:
0.07
10:
0.11
11:
0.04
Negative Logits
byss
-1.30
魔
-1.21
qu
-1.18
ⓘ
-1.14
UCHIJ
-1.13
quished
-1.13
�
-1.11
:=
-1.09
【
-1.08
gal
-1.05
POSITIVE LOGITS
.")
2.28
』
2.13
),"
2.09
)."
2.02
]."
1.95
']
1.89
").
1.88
"]
1.86
"),
1.85
")
1.83
Act
ivations
Density 0.007%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Breaks
Hide Breaks
No Known Activations