INDEX

Explanations

tokens that follow or precede the word "the" or endings of verbs, especially those ending in "ing"

oai_token-act-pair · gemini-2.0-flash

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

parsedMessage

-0.71

 perist

-0.66

脚注の使い方

-0.65

 StatelessWidget

-0.63

 circulaire

-0.63

 honte

-0.61

 Southeastern

-0.61

 gazelle

-0.60

 Morality

-0.59

 porphy

-0.59

POSITIVE LOGITS

曖昧さ回避

0.54

')"

0.54

"]=

0.53

auti

0.49

ConstraintMaker

0.49

“

0.48

+',

0.48

"]="

0.48

)_/¯

0.47

")==

0.46

Activations Density 2.482%

tokens that follow or precede the word "the" or endings of verbs, especially those ending in "ing"

the

No Comments

No Known Activations