INDEX

Explanations

words from the beginning, the middle, and the end of sentences along with some random pronouns and verbs

oai_token-act-pair · gemini-2.0-flash

emotions and reactions to experiences

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

Negative emotions

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

mobileqq

-0.49

reactstrap

-0.44

 sifat

-0.43

ntä

-0.41

 gelungen

-0.41

 onCancelled

-0.41

 censiti

-0.40

saraba

-0.40

IndentedString

-0.39

 hieß

-0.39

POSITIVE LOGITS

 disappointed

1.59

 shocked

1.59

 horrified

1.50

 astonished

1.49

shocked

1.46

 surprised

1.45

 disgusted

1.41

 delighted

1.40

 startled

1.40

 alarmed

1.39

Activations Density 4.193%

words from the beginning, the middle, and the end of sentences along with some random pronouns and verbs

emotions and reactions to experiences

Negative emotions

No Comments

No Known Activations