INDEX

Explanations

terms related to the concept of "dropping."

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

The token "drop"

np_acts-logits-general · gemini-2.0-flash

drop

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 onAnimation

-0.79

 Италијани

-0.69

homonymie

-0.68

 bezeichneter

-0.68

QMetaType

-0.64

 LEYENDO

-0.64

usitis

-0.63

 continúas

-0.63

ArgsConstructor

-0.62

 FishBase

-0.62

POSITIVE LOGITS

 drop

1.41

 drops

1.39

 Drop

1.35

drops

1.31

drop

1.30

Drop

1.26

 dropped

1.25

 dropping

1.24

 DROP

1.22

 Drops

1.22

Activations Density 0.058%

terms related to the concept of "dropping."

The token "drop"

drop

No Comments

No Known Activations