INDEX

Explanations

references to instances of objects or classes in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Welfare

-0.56

legungen

-0.54

Ethical

-0.53

 Calabria

-0.52

Fär

-0.52

getLeft

-0.51

 Educação

-0.50

Selamat

-0.50

 Aragón

-0.50

脚注の使い方

-0.49

POSITIVE LOGITS

 Instance

1.01

Instance

0.99

instance

0.98

 INSTANCE

0.94

 instance

0.93

 getInstance

0.88

INSTANCE

0.85

getInstance

0.82

InstanceId

0.73

inst

0.73

Activations Density 0.167%

references to instances of objects or classes in a programming context

No Comments

No Known Activations