INDEX

Explanations

similes or comparisons expressed as "like."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 estekak

-0.82

 Normdatei

-0.75

WebElementEntity

-0.73

 CreateTagHelper

-0.73

XmlAccessType

-0.72

IsContent

-0.68

Autoritní

-0.66

 ویکی‌پدی

-0.65

 kasarigan

-0.60

ImageContext

-0.60

POSITIVE LOGITS

 distant

0.40

prepareStatement

0.38

makeConstraints

0.38

startActivity

0.36

類

0.35

Like

0.35

 elástica

0.34

 przy

0.32

öglich

0.32

distant

0.32

Activations Density 0.371%

similes or comparisons expressed as "like."

No Comments

No Known Activations

similes or comparisons expressed as "like."

No Comments

No Known Activations