INDEX

Explanations

words associated with politics and war

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoField

-0.76

not

-0.69

principalColumn

-0.67

now

-0.63

 disponibilités

-0.60

ConstraintMaker

-0.59

 nargin

-0.57

+#+#

-0.56

XmlAccessorType

-0.55

mergeFrom

-0.54

POSITIVE LOGITS

AnchorTagHelper

0.58

DotNetBar

0.52

gat

0.50

acrylate

0.49

 excru

0.48

mischer

0.47

atimes

0.47

 harms

0.47

dyn

0.46

 materialism

0.46

Activations Density 4.724%

words associated with politics and war

to

No Comments

No Known Activations