INDEX

Explanations

the word "doing", often with a preceding auxiliary verb and sometimes followed by a word with a weaker association.

oai_token-act-pair · gemini-2.0-flash

doing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 '\\;'

-0.82

ally

-0.78

<bos>

-0.78

 للمعارف

-0.77

 geox

-0.75

ніципа

-0.75

 betweenstory

-0.71

 auffi

-0.69

 Egli

-0.68

 Paglinawan

-0.67

POSITIVE LOGITS

0.66

LayoutPanel

0.63

："

0.61

BagLayout

0.59

 تضيفلها

0.58

rollo

0.57

 most

0.57

makeConstraints

0.56

gulier

0.56

hawatir

0.55

Activations Density 0.818%

the word "doing", often with a preceding auxiliary verb and sometimes followed by a word with a weaker association.

doing

No Comments

No Known Activations