INDEX

Explanations

phrases related to attempts and actions that express conditional situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

stånd

-0.55

endalikan

-0.54

лтамалар

-0.53

 ferme

-0.51

 virtuel

-0.50

borderTop

-0.48

 gepubliceerd

-0.48

RepeatedField

-0.48

fillType

-0.47

Ouv

-0.47

POSITIVE LOGITS

 wrongly

0.71

 inappropri

0.65

 wrong

0.65

wrong

0.64

 inappropriate

0.64

 unsuitable

0.63

SequentialGroup

0.63

اریخ

0.62

 erroneously

0.60

 incorrectly

0.59

Activations Density 0.649%

phrases related to attempts and actions that express conditional situations

No Comments

No Known Activations