INDEX

Explanations

code snippets including copyright notices, years, and code-related terminology

oai_token-act-pair · gemini-2.0-flash

2

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

featureID

-0.67

twimg

-0.67

WithMany

-0.64

istoitu

-0.63

DoubleQuotes

-0.62

 numerus

-0.58

 JsonResult

-0.56

 PopupWindow

-0.56

üyada

-0.56

tagHelperRunner

-0.56

POSITIVE LOGITS

<bos>

1.37

0.83

 ſte

0.67

↵↵

0.63

 Jefus

0.62

ſelf

0.61

’

0.60

 purpoſe

0.60

//

0.57

 Inscrivez

0.56

Activations Density 1.796%

code snippets including copyright notices, years, and code-related terminology

2

No Comments

No Known Activations