INDEX

Explanations

instances of the word "watch" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Soria

-0.62

])),

-0.60

 Clough

-0.57

 idéia

-0.57

 Reim

-0.56

})));

-0.56

aini

-0.56

TextStyle

-0.55

coln

-0.55

dflare

-0.54

POSITIVE LOGITS

 watch

1.52

 Watch

1.41

 WATCH

1.37

 watches

1.36

watch

1.28

 Watched

1.28

 Watches

1.27

Watch

1.26

 watched

1.25

 Watching

1.21

Activations Density 0.087%

instances of the word "watch" and its variations in context

No Comments

No Known Activations