INDEX

Explanations

references to violent or graphic content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

россий

-0.45

awaiter

-0.44

ang

-0.44

-0.43

 tulis

-0.42

身心

-0.42

 peito

-0.41

 despre

-0.41

Const

-0.40

timent

-0.40

POSITIVE LOGITS

 تضيفلها

0.86

PreferredItem

0.83

 Administrativna

0.79

IGraphics

0.78

writeFieldEnd

0.77

 שוליים

0.77

 استنادى

0.76

 الحره

0.76

 '\\;'

0.76

mobileqq

0.73

Activations Density 0.642%

references to violent or graphic content

No Comments

No Known Activations