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

en

-0.52

 dragen

-0.48

せよ

-0.45

dis

-0.45

 conto

-0.43

POINTS

-0.43

sk

-0.42

Copyright

-0.42

kning

-0.42

 before

-0.42

POSITIVE LOGITS

WithIOException

0.94

 Савезне

0.94

AsUp

0.90

 oprot

0.81

oredCriteria

0.79

rungsseite

0.78

Datuak

0.77

ArgsConstructor

0.77

PostBack

0.76

SpringBootTest

0.76

Activations Density 0.081%

No Comments

No Known Activations