INDEX

Explanations

phrases that indicate frequency or intensity of actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

".$

-0.56

 naturais

-0.55

 guías

-0.53

 ural

-0.53

='.$

-0.53

iga

-0.52

="'.$

-0.52

 embl

-0.51

/'.$

-0.51

"")

-0.50

POSITIVE LOGITS

BufferException

0.88

tagHelperRunner

0.84

例句

0.84

#+#

0.83

 gynhyrchwyd

0.82

HasForeignKey

0.82

MLLoader

0.81

featureID

0.81

ImageContext

0.80

sizeCache

0.77

Activations Density 0.211%

phrases that indicate frequency or intensity of actions

No Comments

No Known Activations