INDEX

Explanations

words and phrases related to intimate relations

oai_token-act-pair · gemini-2.0-flash

electric blankets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

OLDS

-0.47

velopes

-0.46

 floss

-0.46

CAPTURE

-0.46

 locks

-0.45

 fold

-0.44

 интерьере

-0.44

 帽子

-0.43

 hangers

-0.43

 hanger

-0.43

POSITIVE LOGITS

tagHelperRunner

0.75

GEBURTSDATUM

0.75

webElementXpaths

0.69

دانشنامهٔ

0.67

RemoveField

0.65

 ویکی‌پدی

0.64

".

0.64

Geplaatst

0.64

 Administrativna

0.62

tadır

0.62

Activations Density 0.764%

words and phrases related to intimate relations

electric blankets

No Comments

No Known Activations