INDEX

Explanations

references to familial relationships, particularly focusing on brothers and siblings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

})));

-0.80

 Lupin

-0.77

 glan

-0.75

DispatchToProps

-0.74

 Judson

-0.73

 smut

-0.73

USERS

-0.72

 ANSI

-0.72

TPM

-0.72

NPs

-0.72

POSITIVE LOGITS

 brother

2.26

 BROTHER

2.17

 brothers

2.15

 Brother

2.07

brother

2.07

Brother

2.03

 Brothers

1.94

 sister

1.88

brothers

1.83

Brothers

1.75

Activations Density 0.052%

references to familial relationships, particularly focusing on brothers and siblings

No Comments

No Known Activations