INDEX

Explanations

references 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ंदीखरीदारी

-0.87

Jeografia

-0.82

esModule

-0.81

 CoreData

-0.80

ⓧ

-0.76

 NSCoder

-0.75

entgen

-0.73

InjectAttribute

-0.69

 noten

-0.69

 AppBundle

-0.69

POSITIVE LOGITS

 align

1.36

align

1.34

 ALIGN

1.32

 Align

1.29

 aligns

1.27

 aligning

1.25

 alignment

1.25

 Alignment

1.22

Align

1.21

alignment

1.19

Activations Density 0.157%

references to alignment in various contexts

No Comments

No Known Activations