INDEX

Explanations

names and familial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 незавершена

-0.66

 Añade

-0.61

ickory

-0.57

webElementXpaths

-0.53

ResponseEntity

-0.50

CVE

-0.49

tiglie

-0.48

ثيل

-0.48

 forKey

-0.48

 TType

-0.47

POSITIVE LOGITS

 leaves

0.95

leaves

0.78

 Leaves

0.72

 leave

0.67

 graduated

0.65

 enjoyed

0.64

Leaves

0.64

 worked

0.64

 loved

0.63

 will

0.62

Activations Density 0.076%

names and familial relationships

No Comments

No Known Activations