INDEX

Explanations

phrases and references related to individuals or characters

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

ArgsConstructor

-0.85

 WebDriverWait

-0.81

 EconPapers

-0.71

BagLayout

-0.70

ConstraintMaker

-0.69

 RouterModule

-0.67

XmlAccessorType

-0.66

HomeAsUpEnabled

-0.66

argout

-0.65

 AppColors

-0.64

POSITIVE LOGITS

who

0.98

ification

0.85

 Persons

0.80

Persons

0.77

 PERSON

0.76

ified

0.75

 PERSONS

0.74

 persons

0.74

 Person

0.73

 person

0.71

Activations Density 0.048%

phrases and references related to individuals or characters

No Comments

No Known Activations