INDEX

Explanations

terms related to diseases and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ţion

-0.73

 extérieurs

-0.73

 ciascuno

-0.73

 arşivlendi

-0.72

 Sheryl

-0.70

 Jurí

-0.70

 giovan

-0.69

 soeur

-0.69

 beslu

-0.67

 empiric

-0.66

POSITIVE LOGITS

 disease

1.48

 diseases

1.46

 Disease

1.31

 Diseases

1.29

Diseases

1.23

 DISEASES

1.23

 DISEASE

1.23

Disease

1.20

disease

1.12

diseases

1.07

Activations Density 0.099%

terms related to diseases and their classifications

No Comments

No Known Activations