INDEX

Explanations

words that are frequently used, such as articles, prepositions, and pronouns

oai_token-act-pair · gemini-2.0-flash

personal stories

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

AndEndTag

-0.90

 kubernetes

-0.87

 IAEA

-0.83

NBS

-0.81

EEU

-0.80

AnimationsModule

-0.79

OLS

-0.78

IHC

-0.77

 AIAA

-0.77

MethodManager

-0.77

POSITIVE LOGITS

ことができました

0.36

Read

0.32

TagMode

0.29

 touch

0.28

ようになりました

0.27

mě

0.26

rač

0.26

 poste

0.26

 ве

0.26

Iden

0.25

Activations Density 40.179%

words that are frequently used, such as articles, prepositions, and pronouns

personal stories

No Comments

No Known Activations