INDEX

Explanations

instances of the word "once" and its variations as transition markers or indicators of a narrative change

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llary

-0.74

 Kardashian

-0.69

GenerationType

-0.67

/**

-0.67

 Marbella

-0.66

 Cordoba

-0.63

 Sweater

-0.62

soort

-0.62

 Córdoba

-0.62

Kami

-0.62

POSITIVE LOGITS

 ONCE

1.35

 Once

1.32

 once

1.29

Once

1.26

once

1.20

ONCE

1.15

 Upon

0.80

Jos

0.79

 UPON

0.77

 upon

0.75

Activations Density 0.055%

instances of the word "once" and its variations as transition markers or indicators of a narrative change

No Comments

No Known Activations