INDEX

Explanations

quantifiable measurements and comparative statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 فريبيس

-0.79

TemporalType

-0.74

mtrl

-0.72

adaptiveStyles

-0.72

MessageTagHelper

-0.70

cookieParser

-0.66

Collegamenti

-0.65

Przypisy

-0.65

AnchorTagHelper

-0.65

Manbalar

-0.64

POSITIVE LOGITS

 nearly

0.68

 least

0.67

 yalnızca

0.63

veria

0.62

venty

0.62

 yüzde

0.60

ruptedException

0.60

nearly

0.57

 totalt

0.56

THAN

0.56

Activations Density 0.223%

quantifiable measurements and comparative statistics

No Comments

No Known Activations