INDEX

Explanations

phrases indicating pending actions or unresolved situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"yet."

np_acts-logits-general · gemini-2.0-flash

not yet

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Референце

-0.56

ViewFeatures

-0.50

PyExc

-0.48

ckså

-0.47

ViewImports

-0.47

PreferredItem

-0.47

الحياه

-0.45

 Wikimedijinoj

-0.44

 autorytatywna

-0.44

sweise

-0.44

POSITIVE LOGITS

yet

0.72

尚未

0.64

 belum

0.63

 chưa

0.60

还没有

0.60

まだ

0.59

 Belum

0.59

还未

0.57

 هنوز

0.56

还没

0.55

Activations Density 0.320%

phrases indicating pending actions or unresolved situations

"yet."

not yet

No Comments

No Known Activations