INDEX

Explanations

mathematical expressions and terminology related to probability and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

uler

-0.56

 Gomes

-0.50

 corner

-0.49

sal

-0.48

 Walsh

-0.47

gub

-0.47

 dwindling

-0.47

amil

-0.46

le

-0.45

POSITIVE LOGITS

adaptiveStyles

0.74

GEBURTSDATUM

0.71

 Италијани

0.68

 kasarigan

0.67

NameInMap

0.65

 muualla

0.65

ViewFeatures

0.65

rungsseite

0.64

Espèce

0.64

 itſelf

0.64

Activations Density 1.652%

mathematical expressions and terminology related to probability and statistics

No Comments

No Known Activations