INDEX

Explanations

mentions of families and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

quer

-0.70

ursos

-0.60

owna

-0.59

 Stoppers

-0.59

 Quay

-0.58

 Correia

-0.57

 Benn

-0.57

 Suede

-0.57

 Amendment

-0.56

ൾ

-0.54

POSITIVE LOGITS

 families

2.49

 Families

2.39

 family

2.38

Families

2.26

family

2.24

 Family

2.22

families

2.20

Family

2.15

 FAMILY

2.09

FAMILY

2.07

Activations Density 0.064%

mentions of families and related terms

No Comments

No Known Activations