INDEX

Explanations

notes and important annotations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

WaitGroup

-0.66

-0.59

buttonShape

-0.59

Enllaces

-0.57

クタイ

-0.56

Conclusión

-0.56

addPreferredGap

-0.56

?>

-0.55

انتهای

-0.55

 跳转至

-0.55

POSITIVE LOGITS

 Note

0.97

Note

0.95

 note

0.92

 NOTE

0.92

NOTE

0.86

 caveat

0.82

note

0.80

 caution

0.63

Disclaimer

0.63

 Nota

0.63

Activations Density 0.212%

notes and important annotations in the text

No Comments

No Known Activations