INDEX

Explanations

technical terms and measurements related to computational algorithms and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueGenerated

-0.49

әне

-0.49

好事

-0.47

Per

-0.46

vily

-0.45

liath

-0.44

raded

-0.44

enoord

-0.44

ัติ

-0.44

mbo

-0.43

POSITIVE LOGITS

 MatDialog

0.80

PreferredItem

0.76

 estekak

0.69

LookAnd

0.62

jfree

0.62

ModelAttribute

0.60

 مشارکت‌کنندگان

0.60

 ་་

0.60

Xna

0.59

 propOrder

0.58

Activations Density 1.438%

technical terms and measurements related to computational algorithms and systems

No Comments

No Known Activations