INDEX

Explanations

terms associated with duration and length

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Diwedd

-0.75

WarningLevel

-0.72

 الحره

-0.68

 للمعارف

-0.66

HKEY

-0.65

wissenschaften

-0.64

קישורים

-0.63

 متعلقه

-0.62

ükemmel

-0.61

Geplaatst

-0.61

POSITIVE LOGITS

 longest

1.58

 length

1.55

 long

1.52

 LONG

1.46

 longer

1.43

 Longest

1.36

long

1.33

length

1.32

Long

1.32

 dài

1.32

Activations Density 0.214%

terms associated with duration and length

No Comments

No Known Activations