INDEX

Explanations

references to specific medications or compounds used in clinical contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

'}>

-0.39

NOPQRST

-0.35

 extremely

-0.35

tra

-0.34

 evidence

-0.34

FunctionType

-0.33

 szá

-0.33

 ideal

-0.32

"}>

-0.31

이

-0.31

POSITIVE LOGITS

ValueStyle

0.75

MemoryWarning

0.73

XmlAccessorType

0.61

 فريبيس

0.61

WaitGroup

0.60

awtextra

0.60

 BorderSide

0.58

Personendaten

0.56

DeleteBehavior

0.56

 ligiloj

0.53

Activations Density 0.469%

references to specific medications or compounds used in clinical contexts

No Known Activations