INDEX

Explanations

instances of the word "certainly", also matching "Are" and "anything"

oai_token-act-pair · gemini-2.0-flash

certainly

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 purpoſe

-1.02

 houſe

-0.99

 abstrait

-0.93

 religieuses

-0.93

 pouvoit

-0.92

 étranger

-0.91

 maroca

-0.91

 aveug

-0.90

 debout

-0.90

 fédé

-0.90

POSITIVE LOGITS

 kasarigan

0.95

SharedDtor

0.94

GEBURTSDATUM

0.88

<bos>

0.87

ThroughAttribute

0.84

 autorytatywna

0.83

]")]

0.81

 calendriers

0.81

/**

0.80

 AspNetCore

0.80

Activations Density 1.286%

instances of the word "certainly", also matching "Are" and "anything"

certainly

No Known Activations