INDEX

Explanations

terms related to medical procedures and patient positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 kasarigan

-0.53

StructEnd

-0.44

ChildScrollView

-0.41

Diweddarwch

-0.41

Története

-0.40

 estekak

-0.40

ValueStyle

-0.39

OGND

-0.38

 AppCompatTheme

-0.37

+#+

-0.37

POSITIVE LOGITS

 position

3.66

 Position

3.27

position

3.14

 positions

3.11

Position

3.02

 POSITION

2.91

 posición

2.80

 Positions

2.73

 posição

2.63

POSITION

2.56

Activations Density 0.904%

terms related to medical procedures and patient positioning

No Comments

No Known Activations