INDEX

Explanations

a jumble of code-related terms, leadership terminology, irc logs, and opinions

oai_token-act-pair · gemini-2.0-flash

out

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 вы

-0.60

 onto

-0.58

 mechanical

-0.52

 ви

-0.52

 Вы

-0.49

Ви

-0.48

Sel

-0.46

Ud

-0.45

gatsby

-0.45

 internetowa

-0.44

POSITIVE LOGITS

 متعلقه

0.93

IntoConstraints

0.81

 للاسماء

0.81

клопе

0.73

 lenker

0.73

tagHelperRunner

0.73

 المعيارى

0.70

 للمعارف

0.67

 >=",

0.66

 createState

0.66

Activations Density 10.678%

a jumble of code-related terms, leadership terminology, irc logs, and opinions

out

No Comments

No Known Activations