INDEX

Explanations

references to medical screening processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 msglen

-0.76

 Dage

-0.68

PreferredItem

-0.67

ImageContext

-0.66

 contextLoads

-0.66

writeFieldEnd

-0.63

Photographs

-0.63

RTGC

-0.63

 ویکی‌پدیا

-0.62

jooq

-0.61

POSITIVE LOGITS

Screening

0.89

 screening

0.88

 Screening

0.87

screening

0.79

 pencil

0.76

 Spanish

0.70

 pencils

0.68

 Pencil

0.67

Spanish

0.64

setcounter

0.63

Activations Density 0.100%

references to medical screening processes

No Comments

No Known Activations