INDEX

Explanations

programmatic elements related to defining and initializing variables or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

δας

-0.48

ynchronously

-0.48

ל

-0.47

↵↵

-0.47

RequestMapping

-0.45

 ujednoznacz

-0.45

 catch

-0.43

InvalidArgument

-0.42

 substanti

-0.42

bat

-0.41

POSITIVE LOGITS

发表于

0.81

 bezeichneter

0.78

<?

0.77

 pinulongan

0.76

="<?=$

0.75

Seeder

0.74

enumii

0.71

 EnglishChoose

0.70

Portály

0.70

tagHelperRunner

0.69

Activations Density 0.798%

programmatic elements related to defining and initializing variables or settings

No Comments

No Known Activations