INDEX

Explanations

uses of "it" and "how" in questions and descriptions of processes and procedures

oai_token-act-pair · gemini-2.0-flash

fines

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.87

numerusform

-0.62

istoitu

-0.57

 PRESENTED

-0.54

tences

-0.54

zám

-0.54

المشاركات

-0.53

 AssemblyCulture

-0.53

resented

-0.52

AnchorStyles

-0.52

POSITIVE LOGITS

 propOrder

0.69

 NgModule

0.51

الحياه

0.48

 كمان

0.47

lew

0.46

WebElement

0.43

grandfather

0.43

CWE

0.43

CET

0.42

CompoundButton

0.42

Activations Density 3.282%

uses of "it" and "how" in questions and descriptions of processes and procedures

fines

No Comments

No Known Activations