INDEX

Explanations

focused expressions of pleading or requests related to not revealing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ویکی‌پدی

-0.50

icians

-0.49

 Anfänger

-0.46

èze

-0.46

manjaro

-0.44

ฯ

-0.44

ones

-0.44

 countryman

-0.44

 indivíduos

-0.43

utorial

-0.43

POSITIVE LOGITS

mom

1.64

dad

1.53

Mom

1.52

Dad

1.51

Mom

1.43

mum

1.35

Dad

1.33

 grandma

1.30

 mommy

1.26

Mum

1.25

Activations Density 0.537%

focused expressions of pleading or requests related to not revealing information

No Comments

No Known Activations