INDEX

Explanations

phrases indicating affiliations or connections to specific entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 שוליים

-0.85

KommentareTeilen

-0.84

principalColumn

-0.82

endphp

-0.81

InputBorder

-0.79

 فريبيس

-0.79

 ElementRef

-0.75

 المعيارى

-0.74

 صوتيه

-0.74

NOPQRST

-0.73

POSITIVE LOGITS

is

0.63

has

0.57

MigrationBuilder

0.55

is

0.55

was

0.47

}}}}

0.46

has

0.45

IS

0.44

↵↵

0.44

WAS

0.44

Activations Density 1.295%

phrases indicating affiliations or connections to specific entities or organizations

No Comments

No Known Activations