INDEX

Explanations

adjectives describing clothing and fashion items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

OGND

-1.04

 NSCoder

-0.89

 Infórmanos

-0.87



-0.85

 juſ

-0.84

 ſever

-0.83

 ſch

-0.82

 oreille

-0.81

 cauſe

-0.81

 ſur

-0.78

POSITIVE LOGITS

0.63

还有一个

0.54

有一個

0.51

有一个

0.51

 כולל

0.48

 also

0.48

 total

0.47

 always

0.46

INCLUDES

0.46

Activations Density 0.216%

adjectives describing clothing and fashion items

No Comments

No Known Activations