INDEX

Explanations

terms related to statistical tests and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 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

 gevallen

-0.35

 nothwendig

-0.34

 čierna

-0.34

-0.32

 beschik

-0.31

BM

-0.31

gehenden

-0.30

SR

-0.30

deutig

-0.30

GB

-0.27

POSITIVE LOGITS

 فريبيس

0.85

 Roskov

0.76

 الرياضيه

0.72

Autoritní

0.72

ViewFeatures

0.71

sizeCache

0.71

 ModelExpression

0.69

पया

0.69

sidemargin

0.68

LabelTagHelper

0.67

Activations Density 1.579%

terms related to statistical tests and values

No Comments

No Known Activations