INDEX

Explanations

phrases indicating actions or processes that involve application or connection

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

 Monfieur

-0.91

 Reſ

-0.89

 Chriftian

-0.81

 Anſ

-0.80

 estimés

-0.80

 Jefus

-0.80

 itſelf

-0.78

 ―――――

-0.78

łoś

-0.78

 MainAxisSize

-0.76

POSITIVE LOGITS

by

2.21

by

1.84

BY

1.77

By

1.72

By

1.59

 oleh

1.48

BY

1.46

mby

1.25

bys

1.24

 توسط

1.23

Activations Density 0.332%

phrases indicating actions or processes that involve application or connection

No Comments

No Known Activations