INDEX

Explanations

words related to unhappiness

oai_token-act-pair · gemini-2.0-flash

emotions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.65

 Picchu

-0.65

 ostavi

-0.53

KURZBESCHREIBUNG

-0.53

 rentrée

-0.53

 nahilalakip

-0.52

 fumée

-0.50

tolua

-0.50

 Dism

-0.50

 demografica

-0.49

POSITIVE LOGITS

at

0.72

fromnode

0.53

queryInterface

0.47

 imageNamed

0.46

rijk

0.45

eadilan

0.45

at

0.45

 {}),

0.43

 StatefulWidget

0.43

At

0.42

Activations Density 1.402%

words related to unhappiness

emotions

No Comments

No Known Activations