INDEX

Explanations

references to "Big" as a significant term or concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

TintMode

-0.83

ItemBackground

-0.81

XmlAccessorType

-0.74

Diweddarwch

-0.73

IsMutable

-0.72

HideFlags

-0.67

ніципалі

-0.64

awtextra

-0.61

TypedDataSet

-0.60

TagHelpers

-0.60

POSITIVE LOGITS

oted

0.78

gie

0.73

 brother

0.70

gies

0.64

otry

0.63

GEST

0.63

 leagues

0.62

fat

0.60

wig

0.60

wigs

0.60

Activations Density 0.144%

references to "Big" as a significant term or concept

No Comments

No Known Activations