INDEX

Explanations

references to various scientific societies 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Sesame

-0.52

FormTagHelper

-0.52

nicamente

-0.52

Slots

-0.51

మీ

-0.51

transQ

-0.50

meg

-0.49

 Numerology

-0.48

verwijspagina

-0.48

bonucleic

-0.48

POSITIVE LOGITS

 Society

1.62

 SOCIETY

1.43

Society

1.36

 Societies

1.06

Soc

1.06

Soc

0.99

tang

0.90

 Tang

0.86

Sociedad

0.85

 TANG

0.85

Activations Density 0.369%

references to various scientific societies and organizations

No Comments

No Known Activations