INDEX

Explanations

references to health-related impacts, particularly due to the coronavirus

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

Sentences that end with "m" or "be"

np_acts-logits-general · gemini-2.0-flash

Coronavirus pandemic

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 repaired

-0.55

 kasarigan

-0.55

 kaarangay

-0.53

enseur

-0.53

 regenerated

-0.52

 reversible

-0.52

Christmas

-0.50

 hefyd

-0.50

 RECOVERY

-0.50

 Recovery

-0.49

POSITIVE LOGITS

Coronavirus

0.86

 Coronavirus

0.85

 coronavirus

0.82

coronavirus

0.67

 quarantined

0.62

 panic

0.60

 Quarantine

0.60

 virus

0.59

 Wuhan

0.57

 coronav

0.57

Activations Density 0.063%

references to health-related impacts, particularly due to the coronavirus

Sentences that end with "m" or "be"

Coronavirus pandemic

No Comments

No Known Activations