INDEX

Explanations

code snippets and category names, especially from technical documents

oai_token-act-pair · gemini-2.0-flash

Technical documentation and code

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

年

-1.06

년

-0.73

年

-0.59

月

-0.52

 thicker

-0.50

ynb

-0.50

withIdentifier

-0.50

 thicken

-0.49

InputTagHelper

-0.47

 упро

-0.47

POSITIVE LOGITS

<bos>

0.98

RegistryLite

0.73

 चीज़ों

0.72

ValueStyle

0.68

Билгалдахарш

0.58

 autorytatywna

0.56

रीदारी

0.55

 picked

0.55

contentLoaded

0.54

 BoxDecoration

0.54

Activations Density 10.079%

code snippets and category names, especially from technical documents

Technical documentation and code

No Comments

No Known Activations