INDEX

Explanations

phrases related to creation and active elements indicating updates or modifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tagHelperRunner

-0.79

RuleContext

-0.69

 EconPapers

-0.60

setupUi

-0.55

XmlAccessType

-0.54

webElementXpaths

-0.54

kään

-0.52

tivitas

-0.51

jooq

-0.51

ArrowToggle

-0.50

POSITIVE LOGITS

ByUser

0.60

YNAMIC

0.58

 Theſe

0.58

By

0.54

By

0.53

 myſelf

0.53

since

0.53

 auprès

0.53

by

0.52

 berço

0.52

Activations Density 0.280%

phrases related to creation and active elements indicating updates or modifications

No Comments

No Known Activations