INDEX

Explanations

the word "divided" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Griffiths

-0.60

 Stein

-0.59

 EXPERI

-0.59

 pituitary

-0.57

 aigu

-0.56

ituitary

-0.56

転

-0.55

nits

-0.54

 Mick

-0.53

 ester

-0.53

POSITIVE LOGITS

 divided

1.41

 divide

1.40

 Divided

1.30

divided

1.29

 Divide

1.29

 divides

1.19

 dividing

1.19

divide

1.17

Divide

1.11

 compromis

0.94

Activations Density 0.131%

the word "divided" in various contexts

No Comments

No Known Activations