INDEX

Explanations

abbreviations followed by periods and associated words such as and, also, helped, read, testified, and conducted.

oai_token-act-pair · gemini-2.0-flash

research papers/legal context

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<bos>

-1.17

’

-0.53

-0.51

<eos>

-0.45

 hés

-0.43

she

-0.42

he

-0.42

 perus

-0.41

ropical

-0.41

 niej

-0.41

POSITIVE LOGITS

parsedMessage

0.90

出版年

0.85

ScopeManager

0.84

Personensuche

0.84

 مرئيه

0.80

 myſelf

0.75

 defaultstate

0.74

 متعلقه

0.73

InSection

0.72

 "..\..\..\

0.71

Activations Density 0.928%

abbreviations followed by periods and associated words such as and, also, helped, read, testified, and conducted.

research papers/legal context

No Comments

No Known Activations