INDEX

Explanations

references to gifts and presenting items

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

кож

-0.57

thâu

-0.56

ValueStyle

-0.55

)$/,

-0.54

']):

-0.53

.*")]

-0.53

')):

-0.52

 endwhile

-0.51

AILABLE

-0.51

utnik

-0.50

POSITIVE LOGITS

 gift

1.85

 gifts

1.79

gift

1.58

 Gift

1.57

 Gifts

1.56

Gift

1.53

Gifts

1.51

gifts

1.47

 GIFT

1.39

 gifting

1.38

Activations Density 0.114%

references to gifts and presenting items

No Comments

No Known Activations