INDEX

Explanations

specific names and locations related to businesses and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 endwhile

-0.60

 Montoya

-0.58

 âmes

-0.57

ंदीखरीदारी

-0.57

 tavo

-0.52

 venezol

-0.52

 Schmitz

-0.51

 gräns

-0.51

 Carcass

-0.49

wani

-0.48

POSITIVE LOGITS

 Boston

1.48

 Massachusetts

1.46

Boston

1.29

Massachusetts

1.28

 boston

1.15

BOSTON

1.13

 BOSTON

1.13

boston

1.06

achusetts

1.04

 Harvard

1.03

Activations Density 0.248%

specific names and locations related to businesses and organizations

No Comments

No Known Activations