INDEX

Explanations

measurements and dimensions in various units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

↵

-0.56

Билгалдахарш

-0.55

-0.54

sol

-0.53

degener

-0.52

 transfieras

-0.51

the

-0.51

łania

-0.51

-0.50

Dey

-0.50

POSITIVE LOGITS

 inches

1.13

 Inches

1.10

inches

1.00

cm

1.00

 centimetres

0.99

GEBURTS

0.98

cm

0.97

 centimeters

0.92

 Inch

0.87

 centimeter

0.86

Activations Density 0.098%

measurements and dimensions in various units

No Comments

No Known Activations