INDEX

Explanations

technical language related to scientific publication, experimental procedures, and data analysis.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 genoux

-0.78

 épaules

-0.63

 jambes

-0.60

 lèvres

-0.59

 vœux

-0.58

 dieux

-0.57

 prochaines

-0.55

 pères

-0.55

 mères

-0.54

 oreilles

-0.53

POSITIVE LOGITS

 itſelf

1.50

 ſmall

1.45

ſelf

1.45

 myſelf

1.41

 ſeveral

1.41

 ſch

1.34

 perfons

1.34

 ſta

1.30

 ſtate

1.30

 Jefus

1.30

Activations Density 9.733%

technical language related to scientific publication, experimental procedures, and data analysis.

No Comments

No Known Activations