INDEX

Explanations

terms related to printing and document manipulation functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

contentLoaded

-0.65

expandindo

-0.64

 مرئيه

-0.64

SourceChecksum

-0.63

afficheront

-0.57

 Paglinawan

-0.55

KommentareTeilen

-0.54

Aholisi

-0.52

MultipartFile

-0.51

ьаж

-0.49

POSITIVE LOGITS

 settings

2.40

settings

1.96

 Settings

1.95

 setting

1.83

Settings

1.76

 SETTINGS

1.66

 configuration

1.65

 Setting

1.63

setting

1.57

Setting

1.52

Activations Density 0.912%

terms related to printing and document manipulation functions

No Comments

No Known Activations