INDEX

Explanations

phrases related to emotional or psychological states

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

)':

-0.61

]**

-0.57

reggio

-0.54

seende

-0.52

 AppModule

-0.51

mapStateToProps

-0.51

μον

-0.50

)":

-0.50

meable

-0.49

 betreft

-0.49

POSITIVE LOGITS

 فريبيس

0.70

 gynhyrchwyd

0.68

脚注の使い方

0.62

 Walkover

0.59

Personensuche

0.57

 Occur

0.56

 виправивши

0.54

IntoConstraints

0.53

Билгалдахарш

0.50

 bear

0.50

Activations Density 0.883%

phrases related to emotional or psychological states

No Comments

No Known Activations