INDEX

Explanations

technical terms related to alignment in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 }}"></

-0.98

expandindo

-0.87

 Мексичка

-0.73

 مشين

-0.73

IVEREF

-0.72

 kaarangay

-0.70

InjectAttribute

-0.70

?>">

-0.69

$_"

-0.69

出版年

-0.68

POSITIVE LOGITS

Alignment

1.08

aligned

0.93

 aligned

0.77

alignment

0.77

align

0.75

 align

0.75

 alignment

0.75

 Alignment

0.72

 alignments

0.63

forall

0.63

Activations Density 0.147%

technical terms related to alignment in various contexts

No Comments

No Known Activations