INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.75

modelBuilder

-0.73

 gainera

-0.69

 betweenstory

-0.68

"},

-0.68

)<<

-0.66

rinfo

-0.66

(!__

-0.65

"]];

-0.65

ulemon

-0.64

POSITIVE LOGITS

SequentialGroup

0.71

KommentareTeilen

0.51

SCHEDULE

0.50

GenerationType

0.50

archiviato

0.46

Referanser

0.46

istoitu

0.45

 schedules

0.45

スケジュール

0.45

 schedule

0.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.