INDEX

Explanations

words associated with expressing opinions, sadness, humor, or agreement

oai_token-act-pair · gemini-2.0-flash

Expressing feelings and opinions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.72

 ISNI

-0.53

WEBPACK

-0.47

sione

-0.46

${(

-0.46

Bue

-0.46

 albu

-0.45

busch

-0.45

Nuorodos

-0.45

Indeed

-0.44

POSITIVE LOGITS

twimg

0.71

 snippetHide

0.66

}{*}{

0.56

UpdateCommand

0.54

omitempty

0.54

NameInMap

0.53

?>

0.52

/*

0.52

러나

0.51

 NSCoder

0.50

Activations Density 6.791%

words associated with expressing opinions, sadness, humor, or agreement

Expressing feelings and opinions

No Comments

No Known Activations