INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 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

 purpoſe

-0.98

 Monfieur

-0.94

 fhew

-0.93

."]

-0.90

 poffible

-0.90

 ―――――

-0.87

 myſelf

-0.87

 becauſe

-0.86

]";

-0.86

()",

-0.85

POSITIVE LOGITS

 Williams

1.23

boldsymbol

1.11

Williams

1.04

 Smith

1.02

mith

1.00

0.95

Kim

0.94

0.93

Kim

0.92

 williams

0.90

Activations Density 0.043%

No Comments

No Known Activations