INDEX

Explanations

testing-related functions and setup routines in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Bourgoin

-0.57

Vys

-0.52

 melanoma

-0.51

 niacin

-0.49

 Communism

-0.49

 chopsticks

-0.47

 Emory

-0.47

 Trọng

-0.46

pot

-0.45

 throm

-0.45

POSITIVE LOGITS

beforeEach

1.73

BeforeEach

1.32

BeforeMethod

1.25

PreExecute

1.03

beforeAll

0.98

 setUp

0.97

BeforeAll

0.93

setupUi

0.91

BeforeClass

0.84

SourceChecksum

0.81

Activations Density 0.045%

testing-related functions and setup routines in code

No Comments

No Known Activations