INDEX

Explanations

acknowledgements or expressions of gratitude in academic papers.

oai_token-act-pair · gemini-2.0-flash

Thanks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 thank

-2.80

thanks

-2.52

thank

-2.50

 thanks

-2.48

 Thank

-2.45

 Thanks

-2.41

Thank

-2.34

 thanking

-2.25

 thanked

-2.25

Thanks

-2.25

POSITIVE LOGITS

 BoxDecoration

0.65

omitempty

0.57

 InputDecoration

0.53

expandindo

0.47

ödie

0.46

 predictor

0.46

сього

0.46

Климат

0.45

predictor

0.44

例句

0.43

Activations Density 1.598%

acknowledgements or expressions of gratitude in academic papers.

Thanks

No Comments

No Known Activations

acknowledgements or expressions of gratitude in academic papers.

Thanks

No Comments

No Known Activations