INDEX

Explanations

references to 'extra' attributes or components in various contexts

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

"extra" followed by a noun

np_acts-logits-general · gemini-2.0-flash

extra before noun

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Naissance

-0.62

 cejas

-0.58

IMS

-0.58

browserify

-0.58

Gos

-0.55

Jen

-0.55

 ciutat

-0.53

 asemenea

-0.53

FormState

-0.52

\}\\

-0.52

POSITIVE LOGITS

 EXTRA

1.42

 Extra

1.40

 extra

1.36

Extra

1.29

 Extras

1.29

extra

1.25

EXTRA

1.23

 extras

1.22

extras

1.15

 ekstra

1.10

Activations Density 0.124%

references to 'extra' attributes or components in various contexts

"extra" followed by a noun

extra before noun

No Comments

No Known Activations