INDEX

Explanations

references to "it"

oai_token-act-pair · gemini-2.0-flash

various forms of the word 'it'

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

Discussion forum comments

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

IFrame

Link

Negative Logits

AndEndTag

-0.63

ɵ

-0.54

Sucesor

-0.54

BASEPATH

-0.52

 comuniques

-0.50

hoeddwyd

-0.50

帖最后由

-0.50

MockBean

-0.49

 resourceCulture

-0.47

tdessen

-0.47

POSITIVE LOGITS

ItemBackground

0.68

 Paglinawan

0.65

 externi

0.54

 asume

0.53

seemed

0.53

到底是

0.52

 depend

0.52

 Depends

0.52

 seemed

0.52

 Biôgrafia

0.52

Activations Density 0.658%

references to "it"

various forms of the word 'it'

Discussion forum comments

No Known Activations