INDEX

Explanations

terms related to health care and health outcomes

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

Relates "health" and other nouns to professionals/beliefs

np_acts-logits-general · gemini-2.0-flash

health professionals and care

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

EndContext

-0.76

InitVars

-0.66

IsMutable

-0.64

IsContent

-0.55

webElementGuid

-0.52

empio

-0.52

 Initiative

-0.51

 SafeArea

-0.51

EndInit

-0.50

setVerticalGroup

-0.50

POSITIVE LOGITS

NUMX

0.68

 GenerationType

0.66

']>;

0.62

tvguidetime

0.60

/*

0.59

 LoggerFactory

0.58

mybatisplus

0.58

 professionals

0.57

prepareStatement

0.57

/**

0.55

Activations Density 0.898%

terms related to health care and health outcomes

Relates "health" and other nouns to professionals/beliefs

health professionals and care

No Comments

No Known Activations