INDEX

Explanations

terms related to statistical analysis and significance testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

SourceChecksum

-0.73

expandindo

-0.54

sizeCache

-0.51

 صوتيه

-0.50

tagext

-0.50

 protoimpl

-0.48

PEN

-0.48

 يتيمه

-0.48

 &___

-0.46

WebVitals

-0.45

POSITIVE LOGITS

2.89

2.02

ｐ

1.30

п

1.29

پ

1.11

𝑝

1.05

प

1.02

pp

1.00

 getP

0.98

Activations Density 1.296%

terms related to statistical analysis and significance testing

No Comments

No Known Activations