INDEX

Explanations

the word "of" and, less often, words that come before or after it.

oai_token-act-pair · gemini-2.0-flash

a

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

-0.69

is

-0.59

-0.55

-0.52

<bos>

-0.52

or

-0.52

-0.51

and

-0.49

And

-0.49

As

-0.48

POSITIVE LOGITS

 تضيفلها

1.10

 مشين

1.06

 ujednoznacz

1.05

rungsseite

0.96

 autorytatywna

0.93



0.93

ंदीखरीदारी

0.92

OGND

0.91

IntoConstraints

0.89

SharedDtor

0.88

Activations Density 11.351%

the word "of" and, less often, words that come before or after it.

a

No Comments

No Known Activations

the word "of" and, less often, words that come before or after it.

a

No Comments

No Known Activations