INDEX

Explanations

programming constructs related to loops and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

setCellValue

-0.37

ENDIAN

-0.35

coledì

-0.33

xlabel

-0.32

ball

-0.31

-0.30

retario

-0.30

savefig

-0.30

ợt

-0.30

nestjs

-0.29

POSITIVE LOGITS

 size

1.09

 length

0.93

size

0.85

 tamanho

0.84

 tamaño

0.83

 SIZE

0.83

 lenght

0.78

 lengths

0.78

 sizes

0.77

 Größe

0.76

Activations Density 0.213%

programming constructs related to loops and conditions

No Comments

No Known Activations