INDEX

Explanations

references to toys and merchandise related to popular culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 CreateTagHelper

-0.72

semibold

-0.70

 Theſe

-0.61

WriteTagHelper

-0.60

hirts

-0.60

вгений

-0.58

󠁿

-0.56

اديم

-0.56

urfacing

-0.55

vaadin

-0.55

POSITIVE LOGITS

toy

1.50

 doll

1.41

 dolls

1.38

 toys

1.30

toy

1.20

Toy

1.16

 Doll

1.15

 Dolls

1.15

Toy

1.11

 Toys

1.07

Activations Density 0.109%

references to toys and merchandise related to popular culture

No Comments

No Known Activations