INDEX

Explanations

technical terms related to attributes and representation in learning systems

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

+:+

-0.60

脚注の使い方

-0.58

featureID

-0.57

 يتيمه

-0.56

 cherchés

-0.53

 OPTIM

-0.53

Optimis

-0.52

 civi

-0.52

RTLI

-0.51

奉

-0.49

POSITIVE LOGITS

 identidade

0.55

 procès

0.54

 identity

0.52

 entity

0.50

 identidad

0.49

 Identität

0.47

 abstracta

0.46

 entities

0.46

identity

0.45

 relations

0.45

Activations Density 0.050%

technical terms related to attributes and representation in learning systems

No Comments

No Known Activations