INDEX

Explanations

statements indicating findings or evidence from studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 المعيارى

-0.70

InitStruct

-0.60

 hierogly

-0.60

olstein

-0.59

AnchorStyles

-0.56

 McGu

-0.56

 allá

-0.56

 Manus

-0.56

 viewDidLoad

-0.55

Materiał

-0.55

POSITIVE LOGITS

TestingModule

0.67

rungsseite

0.54

 quæ

0.54

mapStateToProps

0.53

)}

0.51

--)

0.50

 impreso

0.50

越是

0.49

 Alhambra

0.49

 TestBed

0.48

Activations Density 0.418%

statements indicating findings or evidence from studies

No Comments

No Known Activations