INDEX

Explanations

text about specific household cleaning tasks and items

oai_token-act-pair · gemini-2.0-flash

instructions for cleaning

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

Cleaning and chemicals

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

脚注の使い方

-0.69

oredCriteria

-0.64

@[+][

-0.59

 OFDb

-0.57

wußt

-0.56

Manbalar

-0.56

tawesome

-0.54

 EClass

-0.54

 resourceCulture

-0.53

InstrumentedTest

-0.53

POSITIVE LOGITS

ⓧ

0.61

 незавершена

0.60

gnore

0.58

NgModule

0.50

varet

0.45

LayoutStyle

0.45

 Break

0.43

happ

0.42

naio

0.42

 Ejecutivo

0.42

Activations Density 1.510%

text about specific household cleaning tasks and items

instructions for cleaning

Cleaning and chemicals

No Comments

No Known Activations