INDEX

Explanations

references to quantities or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 estekak

-0.71

 proposito

-0.66

তথ্যসূত্র

-0.64

 समीक्षाओं

-0.60

 مشين

-0.58

RepeatedField

-0.57

Iné

-0.57

 AssemblyCompany

-0.57

Slf

-0.55

lotten

-0.55

POSITIVE LOGITS

amounts

0.79

 amounts

0.72

 Amounts

0.70

 amount

0.70

 owed

0.68

Amounts

0.64

ality

0.62

 payable

0.61

manship

0.61

 الفلك

0.60

Activations Density 0.155%

references to quantities or measurements

No Comments

No Known Activations