INDEX

Explanations

instances of the word "not" or its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

are

-0.73

々は

-0.70

is

-0.68

is

-0.64

 demikian

-0.64

are

-0.62

avond

-0.61

 является

-0.60

 marito

-0.59

 находятся

-0.59

POSITIVE LOGITS

 useAppContext

1.10

 Anſ

1.08

GEBURTSDATUM

1.03

)),

0.98

expandindo

0.97

/>";

0.96

Eſ

0.96

 purpoſe

0.96

ніципалі

0.94

IndentedString

0.94

Activations Density 0.114%

instances of the word "not" or its variations

No Comments

No Known Activations