INDEX

Explanations

words related to directed graphs and probability distributions

oai_token-act-pair · gemini-2.0-flash

directed graphs in code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ImageContext

-0.50

ilever

-0.48

intios

-0.47

 moving

-0.45

牡

-0.44

一家

-0.44

 disulfide

-0.43

 Stray

-0.43

Popular

-0.42

 từng

-0.42

POSITIVE LOGITS

IsContent

0.77

PMailer

0.72

createCanvas

0.68

 لينك

0.66

webElementXpaths

0.64

setupUi

0.61

Controllo

0.61

StructEnd

0.59

oneofs

0.58

 autorytatywna

0.57

Activations Density 2.653%

words related to directed graphs and probability distributions

directed graphs in code

No Comments

No Known Activations