INDEX

Explanations

phrases involving the term "set."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Населення

-0.85

ArrowToggle

-0.81

httphttps

-0.78

 שוליים

-0.74

DoubleQuotes

-0.71

Datuak

-0.70

">—

-0.68

FieldNumber

-0.66

Cordialement

-0.65

Šaltiniai

-0.64

POSITIVE LOGITS

eed

0.56

 Letting

0.56

Kand

0.55

Letting

0.54

Setting

0.54

 Formule

0.54

 screw

0.53

cá

0.53

 bikin

0.53

Lá

0.53

Activations Density 0.200%

phrases involving the term "set."

No Comments

No Known Activations