INDEX

Explanations

statistical terms and data representations in research contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 contenuti

-0.54

 varandra

-0.53

 polvere

-0.51

 insuffisamment

-0.51

SourceChecksum

-0.51

contentLoaded

-0.51

ampung

-0.49

 Longman

-0.49

 pareti

-0.48

żdż

-0.47

POSITIVE LOGITS

IntoConstraints

0.82

CopyWith

0.58

SequentialGroup

0.58

EDEFAULT

0.56

 AssemblyCulture

0.55

 ویکی‌پدیا

0.54

 transfieras

0.53

memoized

0.52

 Chwiliwch

0.51

ticles

0.49

Activations Density 1.854%

statistical terms and data representations in research contexts

No Comments

No Known Activations