INDEX

Explanations

instances of an "O" followed by an apostrophe

oai_token-act-pair · gemini-2.0-flash

Foreign names and words

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

tvguidetime

-0.84

">//

-0.63

expandindo

-0.63

帖最后由

-0.62

providedIn

-0.62

]]);

-0.56

 ISNI

-0.55

 ویکی‌پدیا

-0.55

Trimethyl

-0.54

principalColumn

-0.54

POSITIVE LOGITS

rozco

0.45

 دیکھیے

0.45

SuspendLayout

0.42

FormBuilder

0.41

{?>

0.41

viedo

0.41

 поло

0.40

 rayures

0.40

 suivante

0.39

জন

0.39

Activations Density 2.787%

instances of an "O" followed by an apostrophe

Foreign names and words

No Comments

No Known Activations