INDEX

Explanations

instances of the word "og" and its derivatives or related forms, particularly in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Jereo

-0.66

 esternos

-0.60

ArgsConstructor

-0.58

StoryboardSegue

-0.58

 kasarigan

-0.58

randrange

-0.57

SharedCtor

-0.56

aronder

-0.56

Попис

-0.55

 ModelExpression

-0.55

POSITIVE LOGITS

og

1.26

OG

0.89

ogs

0.71

oga

0.70

ogg

0.68

მ

0.65

 跳转至

0.65

OGND

0.62

ogi

0.62

og

0.61

Activations Density 0.815%

instances of the word "og" and its derivatives or related forms, particularly in scientific or technical contexts

No Comments

No Known Activations