INDEX

Explanations

numerical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 BoxDecoration

-0.81

اریخ

-0.70

 szóci

-0.65

 ویکی‌پدیا

-0.63

şak

-0.63

zydent

-0.63

 باخ

-0.63

 Wür

-0.62

gow

-0.61

σθαι

-0.61

POSITIVE LOGITS

 thousand

0.87

thousand

0.81

Thousand

0.78

 thousands

0.76

Thousands

0.74

thousands

0.73

 tisíc

0.71

 tausend

0.70

 тысяч

0.69

 Thousand

0.69

Activations Density 0.214%

numerical values or measurements

No Comments

No Known Activations