INDEX

Explanations

terms related to large-scale studies and their parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 chopsticks

-0.66

 radium

-0.65

 alphabetically

-0.65

 rationing

-0.61

VersionUID

-0.60

 colpa

-0.59

 glutathione

-0.59

 drapes

-0.59

 ketchup

-0.58

 ovulation

-0.57

POSITIVE LOGITS

Autoritní

0.80

IFORNIA

0.77

 متعلقه

0.74

 pure

0.69

 saites

0.68

(()=>

0.67

YNC

0.66

찮

0.66

Données

0.66

 esboço

0.65

Activations Density 0.425%

terms related to large-scale studies and their parameters

No Comments

No Known Activations