INDEX

Explanations

technical terms and references related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 estimés

-0.85

 raiſ

-0.79

IntoConstraints

-0.75

Efq

-0.73

setVerticalGroup

-0.73

bolista

-0.69

 Allociné

-0.69

 Theſe

-0.68

 Monfieur

-0.68

 initComponents

-0.67

POSITIVE LOGITS

:][

1.00

addContainerGap

0.92

jspx

0.85

ngOnInit

0.80

tpl

0.62

 Wayback

0.62

localctx

0.62

webElementXpaths

0.60

ManyToOne

0.58

OneToMany

0.56

Activations Density 0.013%

technical terms and references related to programming and software development

No Comments

No Known Activations