INDEX

Explanations

terms associated with legal and regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 légales

-0.51

Species

-0.49

 espèce

-0.48

gians

-0.48

law

-0.48

 Verhält

-0.46

CLUD

-0.46

revalidate

-0.46

uera

-0.45

él

-0.43

POSITIVE LOGITS

StoryboardSegue

0.80

ArgsConstructor

0.80

0.74

mybatisplus

0.73

 فريبيس

0.72

 незавершена

0.71

TypedDataSet

0.70

NewUrlParser

0.69

styleType

0.69

 ModelExpression

0.68

Activations Density 0.786%

terms associated with legal and regulatory contexts

No Comments

No Known Activations