INDEX

Explanations

references to statistical significance in research results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

GEBURTSDATUM

-0.87

 Roskov

-0.72

 utafitiHapana

-0.68

SBATCH

-0.68

DeleteBehavior

-0.67

يكب

-0.65

titleMargin

-0.65

Portály

-0.65

 CreateTagHelper

-0.64

bootstrapcdn

-0.64

POSITIVE LOGITS

 Short

0.54

Short

0.50

SHORT

0.49

 shorten

0.47

лиз

0.45

 short

0.44

 Kurz

0.44

flash

0.43

 SHORT

0.43

short

0.42

Activations Density 0.729%

references to statistical significance in research results

No Comments

No Known Activations