INDEX

Explanations

words which are either a) related to textual excerpts or b) nouns/verbs following prepositions or auxillary verbs.

oai_token-act-pair · gemini-2.0-flash

say from

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 from

-2.48

from

-1.86

 FROM

-1.63

จาก

-1.63

 dari

-1.52

 från

-1.49

From

-1.48

 From

-1.41

 từ

-1.38

FROM

-1.38

POSITIVE LOGITS

TintMode

0.75

modelBuilder

0.74

expandindo

0.72

ItemLayout

0.72

fjspx

0.68

 ویکی‌پدیا

0.67

انيف

0.61

 ModelExpression

0.59

DataAnnotations

0.55

 kasarigan

0.55

Activations Density 0.316%

words which are either a) related to textual excerpts or b) nouns/verbs following prepositions or auxillary verbs.

say from

No Comments

No Known Activations