INDEX

Explanations

the Math object and trig functions in code

oai_token-act-pair · gemini-2.0-flash

occurrences of the term "Math"

np_token-act-pair-logits · gpt-4o-mini

Math

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GOTREF

-0.50

//</

-0.50

atória

-0.47

 mẫu

-0.47

odar

-0.46

={<

-0.45

zins

-0.45

isNotNull

-0.44

{#

-0.44

//=

-0.44

POSITIVE LOGITS

 saites

0.60

GEBURTSDATUM

0.59

PickerController

0.59

 apud

0.57

blox

0.56

uxxxx

0.54

reach

0.52

FunctionFlags

0.50

Smarty

0.48

liesslich

0.48

Activations Density 0.632%

the Math object and trig functions in code

occurrences of the term "Math"

Math

No Comments

No Known Activations