INDEX

Explanations

references to numbers and quantities related to groups of people

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

 intptr

-0.49

eBook

-0.48

ScrollPane

-0.48

rawValue

-0.46

findpost

-0.46

 ModelExpression

-0.45

Hrsg

-0.45

ɵɵ

-0.45

点

-0.44

erder

-0.44

POSITIVE LOGITS

Hentet

0.86

 female

0.81

onAttach

0.79

 young

0.76

 persons

0.74

🏻‍♀️

0.74

 people

0.73

 enterprising

0.72

!';

0.72

NUMX

0.70

Activations Density 0.477%

references to numbers and quantities related to groups of people

No Comments

No Known Activations