INDEX

Explanations

references to legal terms and documentation details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

########.

-0.53

 незавершена

-0.46

лятор

-0.45

 الدولى

-0.45

StatusCodes

-0.43

PreferredItem

-0.40

بة

-0.40

Men

-0.40

rap

-0.40

 Industry

-0.39

POSITIVE LOGITS

0.86

 dieux

0.73

 StringField

0.66

ValueStyle

0.64

 évêque

0.63

 prêtres

0.61

Tembelea

0.61

),

0.60

 mourir

0.60

 écout

0.60

Activations Density 1.137%

references to legal terms and documentation details

No Comments

No Known Activations