INDEX

Explanations

references to names, titles, or specific terms

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

 الرياضيه

-0.83

 مرئيه

-0.76

 oprot

-0.72

Obrázky

-0.71

MessageTagHelper

-0.69

 contextLoads

-0.68

Datuak

-0.68

 kasarigan

-0.67

^(@)

-0.67

 myſelf

-0.66

POSITIVE LOGITS

_.

0.53

0.52

 literally

0.49

 Life

0.46

Life

0.45

life

0.45

 onPostExecute

0.44

//

0.44

Personendaten

0.44

Activations Density 0.232%

references to names, titles, or specific terms

No Comments

No Known Activations