INDEX

Explanations

starting points or markers indicating the beginning of new content or sections in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

titleMargin

-0.49

testify

-0.47

 Biôgrafia

-0.45

canestro

-0.44

 ChromeDriver

-0.44

 فريبيس

-0.43

GenerationType

-0.43

BagConstraints

-0.42

outState

-0.42

ApiModelProperty

-0.42

POSITIVE LOGITS

 nahilalakip

0.79

IContainer

0.65

StoryboardSegue

0.53

Carriera

0.52

webElementXpaths

0.52

 autorytatywna

0.50

rungsseite

0.50

 initComponents

0.47

Rhestr

0.45

ISupport

0.44

Activations Density 0.018%

starting points or markers indicating the beginning of new content or sections in a document

No Comments

No Known Activations