INDEX

Explanations

instances of significant emphasis or conclusions in the text

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

 touch

-0.53

GEBURTSDATUM

-0.49

.__

-0.49

loh

-0.48

hieu

-0.48

villes

-0.48

 share

-0.47

 present

-0.47

sip

-0.47

).__

-0.45

POSITIVE LOGITS

 GenerationType

0.88

Hochspringen

0.75

 ویکی‌پدیا

0.74

RectangleBorder

0.73

MigrationBuilder

0.69

ButterKnife

0.69

WithMany

0.67

IntoConstraints

0.66

 通販

0.65

 بيها

0.65

Activations Density 0.811%

instances of significant emphasis or conclusions in the text

No Comments

No Known Activations