INDEX

Explanations

recommendations or suggestions for readers related to books or content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 مرئيه

-0.89

 betweenstory

-0.79

ThroughAttribute

-0.75

AlterField

-0.74

 كومونز

-0.71

 '\\;'

-0.69

 AspNetCore

-0.67

<?

-0.64

 ―――――

-0.64

NameInMap

-0.63

POSITIVE LOGITS

ربعة

0.58

 economia

0.52

 fuite

0.50

 this

0.49

urgia

0.48

this

0.48

enderita

0.47

itiva

0.47

 Umwelt

0.47

Activations Density 0.156%

recommendations or suggestions for readers related to books or content

No Comments

No Known Activations