INDEX

Explanations

medical terms and concepts related to treatment and disorder evaluation

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

Terms abbreviated with parentheses

np_acts-logits-general · gemini-2.0-flash

acronyms with abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 nhiêu

-0.40

 morreu

-0.40

 presents

-0.40

}}}{\

-0.39

 mostrarán

-0.39

 kier

-0.38

pub

-0.38

stdc

-0.38

 Randall

-0.38

-0.37

POSITIVE LOGITS

Geplaatst

0.72

oredCriteria

0.67

Życiorys

0.64

 createSprite

0.64

 DbType

0.63

tly

0.60

 BoxFit

0.60

 فريبيس

0.59

>{"

0.59

pholes

0.59

Activations Density 0.170%

medical terms and concepts related to treatment and disorder evaluation

Terms abbreviated with parentheses

acronyms with abbreviations

No Comments

No Known Activations