INDEX

Explanations

AWS role and permission management terms and structures

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

aws configuration statements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Cic

-0.43

 mental

-0.43

cat

-0.42

pel

-0.42

Cic

-0.41

PEL

-0.40

Pel

-0.40

ooc

-0.40

 jScrollPane

-0.40

ges

-0.39

POSITIVE LOGITS

ंदीखरीदारी

0.60

Personendaten

0.57

 للمعارف

0.53

 autorytatywna

0.51

 CreateTagHelper

0.49

CloseOperation

0.49

webElementXpaths

0.46

rungsseite

0.46

 informée

0.46

 Anordnung

0.44

Activations Density 0.120%

AWS role and permission management terms and structures

aws configuration statements

No Known Activations