INDEX

Explanations

dates, particularly in January

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

łgorzata

-0.69

 مرئيه

-0.69

 Điều

-0.68

schirm

-0.67

бло

-0.66

 Morde

-0.64

hamdu

-0.63

曖昧さ回避

-0.63

 Ambro

-0.62

ervlak

-0.62

POSITIVE LOGITS

 January

1.86

January

1.68

 JANUARY

1.57

Jan

1.56

Jan

1.55

 january

1.55

 Januar

1.51

JAN

1.51

january

1.50

JAN

1.50

Activations Density 0.068%

dates, particularly in January

No Comments

No Known Activations