INDEX

Explanations

terms related to health risks and disease outbreaks

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

Coronavirus, COVID, and related terms

np_acts-logits-general · gemini-2.0-flash

COVID-19 and virus outbreaks

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

curities

-0.64

 termites

-0.58

 annuel

-0.58

 contemporain

-0.55

Vegeu

-0.54

AFTA

-0.54

 giudi

-0.53

 kiện

-0.53

multer

-0.52

POSITIVE LOGITS

 COVID

0.94

 Covid

0.83

COVID

0.81

 vaccine

0.77

 coronavirus

0.76

 covid

0.76

covid

0.73

 Epidemio

0.72

 Coronavirus

0.71

MENAFN

0.71

Activations Density 0.177%

terms related to health risks and disease outbreaks

Coronavirus, COVID, and related terms

COVID-19 and virus outbreaks

No Comments

No Known Activations