INDEX

Explanations

questions and uncertainties about topics or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ویکی‌پدیای

-0.94

دانشنامهٔ

-0.83

脚注の使い方

-0.81

 estekak

-0.80

 مرئيه

-0.78

 незавершена

-0.72

Autoritní

-0.71

UserScript

-0.71

 فريبيس

-0.70

inSlope

-0.69

POSITIVE LOGITS

发表于

0.63

Equ

0.55

 Equally

0.53

 equally

0.52

apart

0.45

Whilst

0.44

 bear

0.44

 bearing

0.43

beforeAll

0.42

it

0.42

Activations Density 0.146%

questions and uncertainties about topics or situations

No Comments

No Known Activations