INDEX

Explanations

mathematical symbols and notation related to equations and expressions

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

Characters appearing before "left"

np_acts-logits-general · gemini-2.0-flash

left

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

$(

-0.58

=$(

-0.58

$|

-0.57

NameInMap

-0.50

MigrationBuilder

-0.50

}=\{

-0.49

GOTREF

-0.49

$\{

-0.49

$(

-0.48

="$(

-0.48

POSITIVE LOGITS

left

1.40

 left

1.25

 LEFT

0.95

 Left

0.93

 leaving

0.87

 leave

0.85

LEFT

0.85

左

0.84

 Leave

0.83

 lasciato

0.82

Activations Density 0.542%

mathematical symbols and notation related to equations and expressions

Characters appearing before "left"

left

No Comments

No Known Activations