INDEX

Explanations

the names of publications and associated roles like "editor".

oai_token-act-pair · gemini-2.0-flash

newsletter, Valerie

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 препратки

-0.58

ANTLR

-0.45

graphy

-0.44

日間

-0.44

ayu

-0.44

Encyklopedia

-0.44

ChromeDriver

-0.44

▼

-0.43

rahmen

-0.43

奉

-0.42

POSITIVE LOGITS

TemporalType

0.65

StoryboardSegue

0.59

*/].

0.58

InitStruct

0.56

MigrationBuilder

0.56

🏻‍♀️

0.56

 Memoriam

0.54

ituaries

0.54

Viitteet

0.52

ViewImports

0.52

Activations Density 1.117%

the names of publications and associated roles like "editor".

newsletter, Valerie

No Comments

No Known Activations