INDEX

Explanations

words related to chemistry, medicine, government organizations, or statistical analysis

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

makeConstraints

-0.82

 يتيمه

-0.82

setVerticalGroup

-0.73

 resourceCulture

-0.72

ReusableCell

-0.70

elesai

-0.68

 članak

-0.66

 BoxFit

-0.64

 andet

-0.63

 AssemblyCulture

-0.63

POSITIVE LOGITS

ordon

0.48

 __('

0.43

McC

0.43

du

0.42

ApiModel

0.42

 Corp

0.42

})();

0.40

="@+

0.40

 boto

0.40

 majors

0.39

Activations Density 8.507%

words related to chemistry, medicine, government organizations, or statistical analysis

No Comments

No Known Activations