INDEX

Explanations

phrases discussing diseases and their implications in a medical context

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

upy

-0.43

 memu

-0.42

Racism

-0.37

 بيت

-0.36

BANK

-0.36

 cách

-0.36

()

-0.36

rec

-0.36

}{@

-0.35

եր

-0.35

POSITIVE LOGITS

 disease

1.74

 diseases

1.70

disease

1.46

 Disease

1.41

 illness

1.40

 disorders

1.39

 illnesses

1.38

 Diseases

1.37

 disorder

1.34

 ailment

1.30

Activations Density 0.758%

phrases discussing diseases and their implications in a medical context

No Comments

No Known Activations