INDEX

Explanations

phrases related to the complexities of human relationships and societal interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

していますが

-0.63

ází

-0.59

いますが

-0.57

嬉しいです

-0.57

kazuje

-0.56

をしています

-0.56

しております

-0.56

っていますが

-0.55

 sanoo

-0.55

っております

-0.55

POSITIVE LOGITS

had

1.57

 hadn

1.53

was

1.36

 could

1.30

 wasn

1.25

had

1.23

 would

1.21

 knew

1.21

 podía

1.19

 belonged

1.18

Activations Density 2.334%

phrases related to the complexities of human relationships and societal interactions

No Comments

No Known Activations