INDEX

Explanations

phrases that convey requests for information or feedback

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

Asks the reader to provide information

np_acts-logits-general · gemini-2.0-flash

let me know / let us know

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

GEBURTSDATUM

-0.77

WithIOException

-0.67

المناصب

-0.65

出版年

-0.59

 دیکھیے

-0.57

RegistryLite

-0.56

öö

-0.56

 insuffisamment

-0.56

ỡng

-0.56

 editados

-0.55

POSITIVE LOGITS

 know

1.24

know

1.00

 Know

0.91

Know

0.89

 knows

0.86

 known

0.81

 weten

0.79

 KNOW

0.74

knows

0.74

KNOW

0.71

Activations Density 0.087%

phrases that convey requests for information or feedback

Asks the reader to provide information

let me know / let us know

No Comments

No Known Activations