INDEX

Explanations

references to years and year-related data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-0.91

 يتيمه

-0.89

]));

-0.85

 صوتيه

-0.79

IntoConstraints

-0.78

 المعيارى

-0.78

ConstraintMaker

-0.78

 LoggerFactory

-0.78

最快更新

-0.77

 mapStateToProps

-0.77

POSITIVE LOGITS

ago

0.70

old

0.65

long

0.63

years

0.62

 years

0.61

LayoutStyle

0.59

ling

0.59

year

0.59

lings

0.57

 olds

0.57

Activations Density 0.087%

references to years and year-related data

No Comments

No Known Activations