INDEX

Explanations

words or phrases related to health and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

LookAnd

-0.67

Brainz

-0.56

DateTimeField

-0.49

 sekal

-0.48

Kaieteur

-0.47

 NgModule

-0.46

 aufgenommen

-0.44

:✨

-0.44

IEnumerator

-0.44

商品説明

-0.43

POSITIVE LOGITS

how

1.00

XmlAccessType

0.86

why

0.79

 related

0.75

how

0.72

its

0.72

 relativi

0.71

 what

0.70

related

0.64

 relation

0.63

Activations Density 0.281%

words or phrases related to health and medical conditions

No Comments

No Known Activations