INDEX

Explanations

terms related to patents and inventions

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

Followed by dates or numbers

np_acts-logits-general · gemini-2.0-flash

dates and time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

createCanvas

-0.68

uldig

-0.54

олові

-0.53

 صوتيه

-0.52

ViewImports

-0.52

Xna

-0.52

 виправивши

-0.51

zieży

-0.50

rungsseite

-0.50

ImageContext

-0.49

POSITIVE LOGITS

 shortly

1.39

 yesterday

1.30

 Thursday

1.30

 Wednesday

1.25

 November

1.24

 February

1.24

 July

1.23

 earlier

1.22

 early

1.22

 Tuesday

1.21

Activations Density 1.552%

terms related to patents and inventions

Followed by dates or numbers

dates and time

No Comments

No Known Activations