INDEX

Explanations

words/phrases that denote a personal connection between people, especially someone helping, guiding, dedicating themselves to, or being proud of someone else.

oai_token-act-pair · gemini-2.0-flash

customer relationships

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ору

-0.46

}^\

-0.46

Zip

-0.45

mô

-0.44

its

-0.44

افي

-0.43

 seal

-0.42

istán

-0.42

 geï

-0.42

[[

-0.42

POSITIVE LOGITS

 ExecuteAsync

0.90

Geplaatst

0.89

 CreateTagHelper

0.79

FontOfSize

0.71

 propOrder

0.71

 forKey

0.70

IntoConstraints

0.68

 otomatig

0.63

клопе

0.62

########.

0.62

Activations Density 0.861%

words/phrases that denote a personal connection between people, especially someone helping, guiding, dedicating themselves to, or being proud of someone else.

customer relationships

No Comments

No Known Activations