INDEX

Explanations

references to familial relationships, specifically siblings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 uſed

-0.88

})));

-0.88

CLR

-0.85

 itſelf

-0.83

 myſelf

-0.82

dci

-0.81

DispatchToProps

-0.80

 Etrus

-0.79

 ſay

-0.77

enment

-0.77

POSITIVE LOGITS

 brother

2.06

 BROTHER

2.04

 brothers

1.99

 Brother

1.93

brother

1.91

Brother

1.88

 Brothers

1.77

brothers

1.70

Brothers

1.59

 sister

1.56

Activations Density 0.041%

references to familial relationships, specifically siblings

No Comments

No Known Activations