INDEX

Explanations

instances of the word "drop" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 odkazy

-0.65

expandindo

-0.61

Portály

-0.59

foss

-0.55

 Uint

-0.54

 lccn

-0.54

 tramonto

-0.54

 lettore

-0.54

 âme

-0.54

esModule

-0.54

POSITIVE LOGITS

 drop

1.19

 Drop

1.12

Drop

1.12

 dropped

1.06

 drops

1.05

 dropping

1.02

dropping

0.99

drop

0.94

 Drops

0.91

 DROP

0.91

Activations Density 0.102%

instances of the word "drop" and its variations in context

No Comments

No Known Activations