INDEX

Explanations

terms and references related to software and file types, particularly those associated with Adobe Flash

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

).]

-0.86

="<?=$

-0.84

 figliu

-0.83

 Haitian

-0.79

tableFuture

-0.78

Yol

-0.78

 Minden

-0.77

Erb

-0.77

 perdón

-0.76

withOpacity

-0.75

POSITIVE LOGITS

Sw

1.52

Sw

1.46

SW

1.37

sw

1.34

sw

1.29

SW

1.20

 Swain

1.17

 Swin

1.15

 Swanson

1.12

 Swans

1.09

Activations Density 0.021%

terms and references related to software and file types, particularly those associated with Adobe Flash

No Known Activations