INDEX

Explanations

terms related to viruses and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ski

-0.88

Ski

-0.87

Nordic

-0.85

 skier

-0.84

 Arctic

-0.83

 skis

-0.83

 reindeer

-0.81

☃

-0.81

 Nordic

-0.81

 Snow

-0.80

POSITIVE LOGITS

 Cleopatra

0.73

Osaka

0.67

ніципалі

0.66

Enders

0.64

 vapeur

0.63

iotensin

0.63

 bụ

0.63

strij

0.62

Tikang

0.61

 Igbo

0.61

Activations Density 1.638%

terms related to viruses and their classifications

No Comments

No Known Activations