INDEX

Explanations

opening tokens or tags in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

licet

-0.71

]='\

-0.62

agens

-0.62

ุม

-0.55

adura

-0.55

 Maker

-0.55

ėk

-0.55

xmm

-0.54

abang

-0.54

ziel

-0.53

POSITIVE LOGITS

migrationBuilder

0.75

 <=",

0.73

sizeCache

0.70

อนไลน์

0.68

+#+#

0.66

出版年

0.65

djangoproject

0.65

ViewImports

0.60

Vidite

0.59

 Alembic

0.59

Activations Density 0.677%

opening tokens or tags in a document

No Comments

No Known Activations