INDEX

Explanations

references to academic articles and research contributions

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 membros

-0.52

 Osten

-0.46

members

-0.44

 miembros

-0.43

parsed

-0.40

zis

-0.40

 trinh

-0.40

utebol

-0.40

Seh

-0.39

EndContext

-0.39

POSITIVE LOGITS

 indisponible

0.76

 estimés

0.72

IsContent

0.72

 Elsevier

0.71

PreferredItem

0.69

ArgsConstructor

0.66

ConstraintMaker

0.66

sizeCache

0.65

 AssemblyCompany

0.64

 EconPapers

0.64

Activations Density 0.317%

references to academic articles and research contributions

No Comments

No Known Activations