INDEX

Explanations

mentions of the New York Times

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"NY" followed by a word

np_acts-logits-general · gemini-2.0-flash

NY Times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

operazione

-0.60

abetes

-0.49

stylesheet

-0.48

MigrationBuilder

-0.48

naut

-0.48

</b>

-0.47

 Bartholomew

-0.47

ugno

-0.47

 potreb

-0.46

Operand

-0.46

POSITIVE LOGITS

orianCalendar

0.87

 OnInit

0.79

InjectMocks

0.79

 Times

0.74

 Knicks

0.72

Times

0.71

SizeF

0.66

 متعلقه

0.66

 Mets

0.65

TIMES

0.64

Activations Density 0.102%

mentions of the New York Times

"NY" followed by a word

NY Times

No Comments

No Known Activations