INDEX

Explanations

mentions of crowds of people

oai_token-act-pair · gemini-2.0-flash

crowd

np_max-act · gemini-2.0-flash

crowd

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

<bos>

-1.05

 Jordan

-0.82

 crowd

-0.77

Jordan

-0.75

 crowds

-0.66

 JORDAN

-0.57

Crow

-0.55

 Crown

-0.53

orianCalendar

-0.52

crowd

-0.51

POSITIVE LOGITS

ConstraintMaker

0.76

Hauptartikel

0.69

manteau

0.69

principalColumn

0.68

NewLabel

0.67

posedge

0.65

حوالہ

0.65

expandindo

0.65

GenerationType

0.65

الدراسه

0.65

Activations Density 0.840%

mentions of crowds of people

crowd

crowd

No Comments

No Known Activations