INDEX

Explanations

references to earning or income-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

+#+#

-0.98

LookAnd

-0.86

 disponibilités

-0.84

/**

-0.83

Susie

-0.82

stateProvider

-0.76

Aholisi

-0.73

mybatisplus

-0.70

TargetException

-0.69

HandlerContext

-0.68

POSITIVE LOGITS

 earned

1.23

 Earned

1.20

 earn

1.20

 Earn

1.14

 earns

1.12

Earn

1.07

 earnings

1.06

arned

1.02

 earning

1.01

earned

1.00

Activations Density 0.098%

references to earning or income-related terms

No Comments

No Known Activations