INDEX

Explanations

sentences that involve dialogue and characters' names

oai_token-act-pair · gemini-2.0-flash

immediately

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

TagMode

-0.66

reportWebVitals

-0.60

GeoNames

-0.60

ionario

-0.56

商品説明

-0.56

ContentAlignment

-0.55

/**

-0.54

altri

-0.54

 تضيفلها

-0.52

ometrica

-0.51

POSITIVE LOGITS

 &___

0.55

 jspb

0.53

oneofs

0.47

hela

0.46

 actionMode

0.46

LETS

0.45

wapV

0.44

摘

0.43

buttonBar

0.43

strophe

0.43

Activations Density 1.397%

sentences that involve dialogue and characters' names

immediately

No Comments

No Known Activations