INDEX

Explanations

technical terminologies related to viruses, particularly focusing on their strains and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

InputBorder

-0.73

 disambiguazione

-0.66

 ujednoznacz

-0.64

GEBURTS

-0.63

AutoField

-0.62

StructEnd

-0.59

RTCK

-0.57

IndentedString

-0.56

localctx

-0.56

Enllaços

-0.55

POSITIVE LOGITS

virus

0.68

 virus

0.67

viruses

0.66

 viruses

0.66

 viral

0.65

 Viruses

0.60

 Virus

0.59

 Viral

0.57

viral

0.53

CoV

0.50

Activations Density 0.217%

technical terminologies related to viruses, particularly focusing on their strains and classifications

No Comments

No Known Activations