INDEX

Explanations

verbs that indicate actions or processes in research or scientific studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Geplaatst

-0.65

 صوتيه

-0.63

 الرياضيه

-0.63

 houſe

-0.60

MigrationBuilder

-0.59

AntiForgeryToken

-0.57

webElementXpaths

-0.56

 ddelweddau

-0.56

 незавершена

-0.56

TestBed

-0.56

POSITIVE LOGITS

 ujednoznacz

0.56

########.

0.56

 therein

0.56

 विश्वसनीयता

0.55

 concernant

0.54

comparing

0.53

cuentes

0.50

jestel

0.49

imed

0.49

ictured

0.48

Activations Density 0.715%

verbs that indicate actions or processes in research or scientific studies

No Comments

No Known Activations