INDEX

Explanations

references to semi-structured or semi-parametric concepts in statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ⓘ

-0.60

볍

-0.55

 Вікіпе

-0.51

zej

-0.51

Население

-0.51

 mực

-0.50

bearing

-0.49

Revenir

-0.49

 StatefulWidget

-0.49

 place

-0.48

POSITIVE LOGITS

 semis

0.79

 Semi

0.74

 semic

0.73

 semi

0.72

 SEMI

0.70

ंदीखरीदारी

0.69

Sem

0.68

SEM

0.68

Sem

0.66

sem

0.65

Activations Density 0.088%

references to semi-structured or semi-parametric concepts in statistical analysis

No Comments

No Known Activations