INDEX

Explanations

references to "King" and related term variations, particularly in a political or cultural context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 leſs

-0.69

 pleaſure

-0.66

 myſelf

-0.64

 Whistler

-0.60

PickerController

-0.60

 Zacks

-0.60

 faſt

-0.58

__(/*!

-0.57

 Lovato

-0.57

Zuz

-0.57

POSITIVE LOGITS

 King

1.01

 KING

0.94

 Kings

0.92

👑

0.86

King

0.84

 king

0.84

 kings

0.83

Kings

0.80

 monarch

0.80

Monarch

0.78

Activations Density 0.080%

references to "King" and related term variations, particularly in a political or cultural context

No Comments

No Known Activations