INDEX

Explanations

words or phrases associated with medical or psychological conditions, particularly ADHD

oai_token-act-pair · gemini-2.0-flash

hyperactivity

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.51

 nakalista

-0.49

cali

-0.44

้

-0.44

SerializedName

-0.43

 amplitude

-0.43

 odkazy

-0.43

 Qualitative

-0.42

elernt

-0.42

 kasarigan

-0.42

POSITIVE LOGITS

UseVisualStyle

0.65

 mecán

0.62

InSection

0.59

expandindo

0.57

 تضيفلها

0.56

})]

0.56

 useStyles

0.55

✨:

0.54

міністра

0.54

 Numerade

0.53

Activations Density 0.553%

words or phrases associated with medical or psychological conditions, particularly ADHD

hyperactivity

No Comments

No Known Activations