INDEX

Explanations

terms associated with body language and the body itself

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Squal

-0.88

 quartzite

-0.84

 acorns

-0.83

transQ

-0.82

 gneiss

-0.81

Caw

-0.81

 sharpening

-0.81

 Zuma

-0.79

 Marquette

-0.78

 Nautilus

-0.75

POSITIVE LOGITS

 Body

1.42

 BODY

1.39

body

1.35

Bod

1.34

 body

1.34

 bodies

1.30

Bod

1.27

 Bodies

1.25

Body

1.21

 bodys

1.19

Activations Density 0.071%

terms associated with body language and the body itself

No Comments

No Known Activations