INDEX

Explanations

terms related to processes and evaluations in scientific and technical contexts

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

Follows abbreviations, names, or codes

np_acts-logits-general · gemini-2.0-flash

police officer

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 imidlertid

-0.54

 medarbe

-0.53

 dönt

-0.52

šené

-0.52

-0.51

-0.50

cosity

-0.49

 väx

-0.48

 definitely

-0.48

 basically

-0.48

POSITIVE LOGITS

+:+

0.72

 arşivlendi

0.69

 دیکھیے

0.66

 Paglinawan

0.66

Personendaten

0.65

 الرياضيه

0.64

uxxxx

0.64

 Roskov

0.63

>*/

0.63

StoreMessageInfo

0.62

Activations Density 1.147%

terms related to processes and evaluations in scientific and technical contexts

Follows abbreviations, names, or codes

police officer

No Comments

No Known Activations