INDEX

Explanations

phrases related to relationships and connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 proportional

-0.44

 ivelany

-0.43

 prisma

-0.42

BrowserModule

-0.41

 Савезне

-0.40

+#+#

-0.40

Життєпис

-0.39

BindingResult

-0.38

 logic

-0.38

authService

-0.37

POSITIVE LOGITS

the

0.78

 this

0.59

 these

0.54

 what

0.51

 nonUne

0.50

various

0.48

 various

0.47

biele

0.46

かわらず

0.45

 către

0.45

Activations Density 2.082%

phrases related to relationships and connections between entities

No Comments

No Known Activations