INDEX

Explanations

references to government officials and their roles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Soorten

-0.59

Hozzáférés

-0.51

ametro

-0.48

:]:

-0.48

LDAP

-0.48

Javadoc

-0.47

ecutive

-0.45

מא

-0.45

 Tortoise

-0.44

 weevil

-0.44

POSITIVE LOGITS

 minister

1.58

 Minister

1.49

 ministry

1.42

Minister

1.40

minister

1.38

 ministers

1.37

 Ministers

1.30

 ministries

1.29

minist

1.28

 MINISTER

1.28

Activations Density 0.132%

references to government officials and their roles or positions

No Comments

No Known Activations