INDEX

Explanations

references to skills, abilities, and contributions of individuals in various contexts

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

期刊论文

-0.61

expandindo

-0.60

LookAnd

-0.47

uxxxx

-0.47

UrlResolution

-0.46

 мәкал

-0.45

ंदीखरीदारी

-0.44

verwijspagina

-0.43

awtextra

-0.42

 怎样

-0.42

POSITIVE LOGITS

 skills

0.76

 skill

0.66

 talents

0.63

skills

0.62

Skills

0.55

技能

0.54

 SKILLS

0.54

 Talents

0.53

 skilled

0.53

 Skills

0.52

Activations Density 0.018%

references to skills, abilities, and contributions of individuals in various contexts

No Comments

No Known Activations