INDEX

Explanations

active verbs related to usage and actions involving software or technology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<?

-0.79

SuppressMessage

-0.78

rrggbb

-0.76

XmlAccessType

-0.76

homonymie

-0.74

 BoxFit

-0.74

webElementXpaths

-0.72

AndEndTag

-0.69

 BorderLayout

-0.66

 '\\;'

-0.65

POSITIVE LOGITS

Референце

0.62

 igjen

0.62

 constater

0.60

 envers

0.56

 expériment

0.55

 izdel

0.54

 this

0.53

 eccl

0.53

 právě

0.53

 χρήση

0.53

Activations Density 0.373%

active verbs related to usage and actions involving software or technology

No Comments

No Known Activations