INDEX

Explanations

elements and tags used in HTML and JavaScript code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 للاسماء

-0.63

 Central

-0.57

<eos>

-0.55

HasColumnName

-0.54

 autorytatywna

-0.52

WriteLiteral

-0.52

pry

-0.50

 yağ

-0.49

Central

-0.49

neus

-0.49

POSITIVE LOGITS

ſelves

0.79

^(@)

0.73

ſelf

0.69

 auffi

0.68

elfare

0.67

rrggbb

0.67

UserScript

0.65

wikidata

0.64

 Arkivert

0.64

wiſe

0.62

Activations Density 0.059%

elements and tags used in HTML and JavaScript code

No Comments

No Known Activations