INDEX

Explanations

terms related to legal and occupational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

or

-0.70

and

-0.63

-0.52

 виправивши

-0.51

RectangleBorder

-0.51

 onOptions

-0.50

 <<<<<<<<<<<<<<

-0.46

 المعيارى

-0.44

 мәкал

-0.43

POSITIVE LOGITS

 تضيفلها

0.83

VersionUID

0.71

 Barbier

0.69

AtIndexPath

0.67

 оригіналу

0.67

InlineData

0.66

 Nazionale

0.65

 transférez

0.64

IVID

0.62

liefert

0.61

Activations Density 1.548%

terms related to legal and occupational contexts

No Comments

No Known Activations