INDEX

Explanations

terms related to viruses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 palk

-0.65

thodon

-0.62

 forth

-0.59

 redor

-0.58

 Poche

-0.58

etan

-0.57

 mourut

-0.55

Extra

-0.55

Ber

-0.55

Dob

-0.55

POSITIVE LOGITS

 viruses

1.59

 virus

1.58

 Virus

1.54

 Viruses

1.49

Virus

1.49

virus

1.41

viruses

1.22

onavirus

1.18

VIR

1.11

 coronavirus

1.09

Activations Density 0.212%

terms related to viruses

No Comments

No Known Activations