INDEX

Explanations

medical and healthcare-related terms, particularly focused on specific specialties and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ddelweddau

-0.58

tangentMode

-0.58

yyq

-0.57

AutoField

-0.57

astéro

-0.55

EDEFAULT

-0.55

SourceChecksum

-0.54

 escova

-0.53

TargetException

-0.53

parsedMessage

-0.52

POSITIVE LOGITS

 bowling

0.36

Spelling

0.35

 adiv

0.34

 cricket

0.34

 Forestry

0.34

PasswordField

0.34

 olfactory

0.33

 mice

0.33

 textiles

0.33

Religious

0.33

Activations Density 1.077%

medical and healthcare-related terms, particularly focused on specific specialties and conditions

No Comments

No Known Activations