INDEX

Explanations

phrases that indicate patient status and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

्रीय

-0.50

acyjny

-0.48

typeDefinition

-0.48

rashed

-0.47

bootstrapcdn

-0.47

ervare

-0.46

 interrupted

-0.46

 branching

-0.46

OGND

-0.45

Batis

-0.44

POSITIVE LOGITS

etheless

0.58

 fubject

0.57

 eligible

0.56

parsedMessage

0.54

CppMethod

0.53

spender

0.53

 GetEnumerator

0.53

✨:

0.53

ParallelGroup

0.53

 improperly

0.52

Activations Density 0.424%

phrases that indicate patient status and medical conditions

No Comments

No Known Activations