INDEX

Explanations

phrases related to capabilities and functionalities of products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

حي

-0.50

viewDidLoad

-0.50

TestingModule

-0.48

 SqlCommand

-0.48

champion

-0.46

poise

-0.46

eamento

-0.45

OGND

-0.45

MockBean

-0.45

Checking

-0.45

POSITIVE LOGITS

 either

0.76

ScopeManager

0.71

IsMutable

0.70

Either

0.68

 Either

0.67

either

0.65

 customize

0.65

owohl

0.64

 entweder

0.63

 interchangeably

0.62

Activations Density 0.244%

phrases related to capabilities and functionalities of products or services

No Comments

No Known Activations