INDEX

Explanations

elements related to tattoos and personal grooming attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Viitteet

-0.60

 ͡°)

-0.57

ègre

-0.55

/***/

-0.55

"}")

-0.54

ArgsConstructor

-0.51

__))

-0.51

 JPanel

-0.50

easing

-0.50

enoord

-0.50

POSITIVE LOGITS

 tattoos

1.15

 tattoo

1.11

 Nails

1.11

 nails

1.11

Nails

1.08

 manicure

1.06

 haircut

1.05

 Tattoo

1.00

 Tattoos

1.00

 haircuts

0.98

Activations Density 0.092%

elements related to tattoos and personal grooming attributes

No Comments

No Known Activations