INDEX

Explanations

names, particularly of individuals and their associations

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

NameInMap

-0.84

mybatisplus

-0.83

хьтан

-0.82

webElementXpaths

-0.77

 EconPapers

-0.72

tanleria

-0.71

Jeografia

-0.70

 Chwiliwch

-0.69

 ujednoznacz

-0.68

цездатний

-0.68

POSITIVE LOGITS

 aérienne

0.27

glEnd

0.26

 forêt

0.23

 cardíaca

0.21

 solche

0.21

 sandalias

0.20

 impresa

0.20

 laikā

0.20

 peines

0.20

 esposa

0.20

Activations Density 0.078%

names, particularly of individuals and their associations

No Comments

No Known Activations