INDEX

Explanations

references to technical terms and concepts related to applications and procedural actions in a specialized field

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Boba

-0.50

 kasarigan

-0.49

ska

-0.49

 IDisposable

-0.44

 Jockey

-0.44

 ResultSet

-0.44

ajoz

-0.43

 Glau

-0.43

 Retrofit

-0.42

 Pesto

-0.42

POSITIVE LOGITS

RegressionTest

0.87

 transfieras

0.85

AutoScale

0.83

 CURIAM

0.81

 igång

0.81

TestingModule

0.79

SharedCtor

0.74

aarrggbb

0.72

 ویکی‌پدیای

0.72

HasAnnotation

0.70

Activations Density 1.227%

references to technical terms and concepts related to applications and procedural actions in a specialized field

No Comments

No Known Activations