INDEX

Explanations

references to human characteristics and personal relations

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Not in Any Lists

No Comments

Negative Logits

########.

-0.67

esserung

-0.56

moire

-0.56

jalá

-0.55

 uncles

-0.55

 grandparents

-0.53

 virginity

-0.52

 unknownFields

-0.52

endregion

-0.51

 bowels

-0.50

POSITIVE LOGITS

 person

0.76

новниш

0.70

 Person

0.69

person

0.68

 PERSON

0.65

Население

0.64

 humaines

0.64

 profiles

0.61

 userSchema

0.60

 whom

0.60

Activations Density 0.898%

references to human characteristics and personal relations

No Comments

No Known Activations