INDEX

Explanations

terms related to viruses and their infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 forth

-0.68

Dek

-0.63

 palk

-0.62

down

-0.61

thodon

-0.61

Tü

-0.60

склю

-0.59

 setObject

-0.59

ɓ

-0.59

Dek

-0.58

POSITIVE LOGITS

 viruses

1.44

 virus

1.42

 Virus

1.38

Virus

1.31

 Viruses

1.31

virus

1.26

 coronavirus

1.23

IRUS

1.16

onavirus

1.16

 Coronavirus

1.13

Activations Density 0.174%

terms related to viruses and their infections

No Comments

No Known Activations