INDEX

Explanations

references to morning activities or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

enumi

-0.91

########.

-0.71

ⓧ

-0.71

AndEndTag

-0.64

SourceChecksum

-0.64

 esternos

-0.63

TextLabel

-0.63

ẹo

-0.63

protoimpl

-0.60

IsContent

-0.60

POSITIVE LOGITS

 morning

1.50

 mornings

1.46

 Morning

1.45

 MORNING

1.34

Morning

1.29

morning

1.28

 Morn

1.26

 morn

1.19

 breakfast

1.19

 Breakfast

1.15

Activations Density 0.076%

references to morning activities or programming

No Comments

No Known Activations