INDEX

Explanations

statements that indicate returning values from functions or methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

of

-0.52

here

-0.49

or

-0.48

-0.46

and

-0.44

Ș

-0.43

 closely

-0.43

HERE

-0.43

дца

-0.42

POSITIVE LOGITS

return

2.10

 return

1.44

 Return

1.36

 RETURN

1.32

 дописавши

1.30

migrationBuilder

1.28

 Returns

1.26

 مشين

1.24

ंदीखरीदारी

1.24

 returns

1.20

Activations Density 0.046%

statements that indicate returning values from functions or methods

No Comments

No Known Activations