INDEX

Explanations

phrases that indicate causation or a sense of consequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Hage

-0.57

jMenuItem

-0.57

gorm

-0.50

}>{

-0.50

Naomi

-0.50

 Hickory

-0.49

 Naomi

-0.49

 NOTE

-0.48

prepareStatement

-0.48

greenrobot

-0.48

POSITIVE LOGITS

Makes

0.82

rawDesc

0.70

WaitGroup

0.70

RegistryLite

0.69

 BorderSide

0.67

 Makes

0.65

oporosis

0.64

makes

0.64

 MAKES

0.64

 otomatig

0.63

Activations Density 0.254%

phrases that indicate causation or a sense of consequence

No Comments

No Known Activations