INDEX

Explanations

references to siblings, specifically brothers, in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

})));

-0.82

CLR

-0.81

isticated

-0.71

 Gandalf

-0.71

 Vuitton

-0.68

 ANSI

-0.68

"]}

-0.67

 virt

-0.67

ctuation

-0.66

GHS

-0.66

POSITIVE LOGITS

 BROTHER

1.59

 brother

1.51

brother

1.48

 brothers

1.46

Brother

1.43

 sister

1.41

 Brother

1.39

 Sister

1.30

Sister

1.30

brothers

1.29

Activations Density 0.060%

references to siblings, specifically brothers, in various contexts

No Comments

No Known Activations