INDEX

Explanations

references to novelty or newness in various contexts

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

"New" preceding nouns

np_acts-logits-general · gemini-2.0-flash

new evidence, data, molecules, stars, ideas

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AddTagHelper

-0.42

 CHtml

-0.39

oredCriteria

-0.38

čas

-0.37

XmlAccessorType

-0.35

pingente

-0.34

primaryKey

-0.34

routeProvider

-0.33

enderror

-0.33

execSQL

-0.32

POSITIVE LOGITS

new

1.31

 nuevos

1.23

new

1.22

 nuevo

1.20

 nieuwe

1.20

 nueva

1.19

 nuovo

1.14

 nuovi

1.14

 neue

1.13

新的

1.13

Activations Density 0.541%

references to novelty or newness in various contexts

"New" preceding nouns

new evidence, data, molecules, stars, ideas

No Comments

No Known Activations