INDEX

Explanations

specific medical and health-related terminologies related to diseases and treatment processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

printStackTrace

-0.63

kloped

-0.60

fromnode

-0.57

 تضيفلها

-0.57

+#+

-0.57

*************/

-0.55

AutoScale

-0.54

inction

-0.54

***************/

-0.54

Naissance

-0.54

POSITIVE LOGITS

 Federal

0.89

 federal

0.83

 LCCN

0.81

Federal

0.80

 federally

0.76

 FEDERAL

0.76

WASHINGTON

0.73

 USDA

0.71

 otomatig

0.70

federal

0.67

Activations Density 1.505%

specific medical and health-related terminologies related to diseases and treatment processes

No Comments

No Known Activations