INDEX

Explanations

the presence of the word "in" used frequently

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 ་་

-0.89

 Chriftian

-0.83

 itſelf

-0.80

 Hadrian

-0.80

 Monfieur

-0.79

 Hopf

-0.79

 ―――――

-0.79

 purpoſe

-0.77

 Anſ

-0.77

 Aphrodite

-0.76

POSITIVE LOGITS

the

1.19

in

1.15

IN

1.14

In

1.09

 isIn

0.91

0.90

 accordance

0.89

 lieu

0.86

In

0.84

Dalam

0.84

Activations Density 1.106%

the presence of the word "in" used frequently

No Comments

No Known Activations