INDEX

Explanations

punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 препратки

-0.77

 فريبيس

-0.76

setVerticalGroup

-0.74

FunctionFlags

-0.71

onsored

-0.68

UnitTesting

-0.68

ViewImports

-0.67

"}}

-0.64

uyện

-0.64

adhyay

-0.63

POSITIVE LOGITS

 مُعرِّف

0.69

enumii

0.68

ChildScrollView

0.66

zugehen

0.66

enumi

0.66

 MainAxisSize

0.65

nio

0.64

archiviato

0.63

Kaw

0.63

IsPostBack

0.62

Activations Density 0.007%

punctuation marks

No Comments

No Known Activations