INDEX

Explanations

phrases indicating lists or collections of items or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 समीक्षक

-0.50

 jLabel

-0.49

cshtml

-0.47

")==

-0.47

ExtendWith

-0.47

XmlAccessType

-0.46

Jereo

-0.46

 mulia

-0.45

Зноскі

-0.45

oxidants

-0.45

POSITIVE LOGITS

 disponibilités

0.78

Rhestr

0.73

+#+#

0.73

 BoxFit

0.66

 mergeFrom

0.65

Geplaatst

0.62

enterOuterAlt

0.60

挙

0.59

findpost

0.56

PreferredItem

0.56

Activations Density 0.611%

phrases indicating lists or collections of items or ideas

No Comments

No Known Activations