INDEX

Explanations

instances of writing and typing activities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

i write this

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 SqlDbType

-0.52

 apoder

-0.48

Personendaten

-0.47

@"/

-0.45

 zabud

-0.44

ดับ

-0.44

Ered

-0.42

省市镇

-0.41

 zwykle

-0.41

illots

-0.41

POSITIVE LOGITS

featureID

0.46

 endblock

0.44

 NSCoder

0.42

 kaynağından

0.41

zzleHttp

0.40

VersionUID

0.40

dafx

0.40

writing

0.38

<?

0.37

invokeLater

0.37

Activations Density 0.010%

instances of writing and typing activities

i write this

No Known Activations