INDEX

Explanations

instances of the words "fill" and "filled" along with their derivatives, indicating actions related to filling or occupying space

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

الإنجليزية

-0.72

出版年

-0.64

 متعلقه

-0.60

 rito

-0.59

 vulga

-0.59

 Elvira

-0.58

 asupra

-0.58

cơ

-0.57

Према

-0.57

 tweezers

-0.56

POSITIVE LOGITS

 filled

1.57

 filling

1.56

 fill

1.54

 fills

1.54

filling

1.48

 Fill

1.45

filled

1.44

 Filling

1.40

Filling

1.39

 FILL

1.38

Activations Density 0.181%

instances of the words "fill" and "filled" along with their derivatives, indicating actions related to filling or occupying space

No Comments

No Known Activations