INDEX

Explanations

acknowledgments and contributions from authors in a scientific paper

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

joba

-0.51

">//

-0.48

UnusedPrivate

-0.46

docx

-0.45

}=-\

-0.44

cout

-0.44

例文帳に追加

-0.44

 Horiz

-0.43

 houden

-0.43

SwingConstants

-0.42

POSITIVE LOGITS

RegressionTest

0.86

PreferredItem

0.70

ItemBackground

0.69

 المعيارى

0.68

 <=",

0.65

 recul

0.63

RTLR

0.60

Efq

0.60

 ویکی‌پدیا

0.59

DockStyle

0.59

Activations Density 0.438%

acknowledgments and contributions from authors in a scientific paper

No Comments

No Known Activations