INDEX

Explanations

references to training and educational programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

//

-0.67

 særlig

-0.64

dataclass

-0.56

 télécharger

-0.56

 joindre

-0.55

 spéciaux

-0.54

 poderosos

-0.54

 pertanto

-0.53

 opérateur

-0.52

/>";

-0.52

POSITIVE LOGITS

 training

0.89

 logistics

0.73

training

0.72

 Training

0.69

 TRAINING

0.66

Training

0.66

 Logistics

0.66

AnchorStyles

0.65

Logistics

0.64

 useRef

0.64

Activations Density 0.147%

references to training and educational programs

No Comments

No Known Activations