INDEX

Explanations

terms related to models, strategies, and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

脚注の使い方

-1.22

endphp

-1.11

ChildScrollView

-1.07

 nahilalakip

-1.06

+#+#

-1.05

 '\\;'

-1.05

posedge

-1.02

#+#

-1.02

RectangleBorder

-0.99

 Lightboxes

-0.98

POSITIVE LOGITS

0.71

↵

0.68

0.60

0.55

 that

0.52

0.51

at

0.48

or

0.46

0.45

 more

0.45

Activations Density 1.377%

terms related to models, strategies, and organizational structures

No Comments

No Known Activations