INDEX

Explanations

phrases related to measurement and rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Portale

-0.65

makeConstraints

-0.57

AddHtmlAttribute

-0.52

Життєпис

-0.51

 الرياضيه

-0.51

 Infórmanos

-0.51

 Normdatei

-0.50

VersionUID

-0.50

mybatisplus

-0.49

TypedDataSet

-0.48

POSITIVE LOGITS

 heaviest

0.55

 highest

0.54

 best

0.52

Longest

0.52

highest

0.52

 largest

0.51

nearest

0.50

best

0.50

 longest

0.49

 nearest

0.49

Activations Density 0.712%

phrases related to measurement and rankings

No Comments

No Known Activations