INDEX

Explanations

instances of various quantifiable measures or statistics related to health and medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 disambiguazione

-0.55

almo

-0.50

IMAN

-0.50

xsi

-0.49

etc

-0.48

Red

-0.47

ënt

-0.47

Anyway

-0.47

Th

-0.46

 Anyway

-0.46

POSITIVE LOGITS

 especially

1.39

particularly

1.33

 particularly

1.32

Especially

1.32

especially

1.31

 zowel

1.21

 Especially

1.21

 Particularly

1.20

 sowohl

1.17

 zarówno

1.15

Activations Density 0.440%

instances of various quantifiable measures or statistics related to health and medical research

No Comments

No Known Activations