INDEX

Explanations

instances of the word "stand" and its variations in different contexts, particularly related to physical positioning and action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

الحياه

-0.56

 autorytatywna

-0.56

 muualla

-0.53

 kaarangay

-0.51

CID

-0.48

 AppCompatTheme

-0.47

wege

-0.47

RegressionTest

-0.47

 Abril

-0.46

Diweddarwch

-0.46

POSITIVE LOGITS

 Stand

1.37

 STAND

1.35

Stand

1.32

 stand

1.32

 standing

1.22

 stands

1.16

 Stands

1.14

 stood

1.13

 Standing

1.12

Standing

1.09

Activations Density 0.107%

instances of the word "stand" and its variations in different contexts, particularly related to physical positioning and action

No Comments

No Known Activations