INDEX

Explanations

personal pronouns and words frequently associated with people

oai_token-act-pair · gemini-2.0-flash

who

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

and

-0.79

doing

-0.69

ChildIndex

-0.69

letting

-0.66

 doing

-0.65

carrying

-0.65

speaking

-0.65

 sharing

-0.65

showing

-0.65

 driving

-0.64

POSITIVE LOGITS

0.63

0.52

0.50

 FileReader

0.50

 EventArgs

0.50

ˈ

0.49

ever

0.49

ethe

0.48

’

0.48

et

0.47

Activations Density 12.798%

personal pronouns and words frequently associated with people

who

No Comments

No Known Activations