INDEX

Explanations

elements related to scientific terminologies and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Demografia

-0.60

ChildScrollView

-0.53

ériale

-0.51

衛門

-0.51

 sputnik

-0.50

splitlines

-0.49

chatron

-0.46

ppone

-0.46

Dys

-0.45

ormány

-0.45

POSITIVE LOGITS

AndEndTag

0.78

StoryboardSegue

0.77

 unknownFields

0.72

Искәрмәләр

0.67

 linkovi

0.65

 estekak

0.63

QMetaType

0.63

fjspx

0.61

/*---

0.60

tvguidetime

0.60

Activations Density 2.017%

elements related to scientific terminologies and methodologies

No Comments

No Known Activations