INDEX

Explanations

phrases indicating quality or state of being

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

"Well" followed by a positive adjective

np_acts-logits-general · gemini-2.0-flash

well known, established, aware

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WebVitals

-0.79

 kasarigan

-0.77

RegistryLite

-0.74

 ſeveral

-0.74

esModule

-0.74

zarchiwizowane

-0.73

клопе

-0.72

 Jefus

-0.71

 незавершена

-0.71

 soigneusement

-0.70

POSITIVE LOGITS

 known

0.61

 established

0.55

 versed

0.48

 represented

0.48

 positioned

0.46

nigh

0.46

known

0.46

 suited

0.45

 equipped

0.45

Sto

0.45

Activations Density 0.089%

phrases indicating quality or state of being

"Well" followed by a positive adjective

well known, established, aware

No Comments

No Known Activations