INDEX

Explanations

instances of the word "addition" and its variations in the context of enhancements or new components

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

addition to

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

glBindBuffer

-0.52

 Lawler

-0.50

ardecer

-0.50

userProfile

-0.48

 Barcel

-0.48

 Suivez

-0.47

 Steering

-0.47

scrollY

-0.47

cemic

-0.46

EndTag

-0.46

POSITIVE LOGITS

 addition

1.15

addition

1.07

 Addition

1.06

 additions

1.06

Addition

1.03

 Additions

0.96

Additions

0.84

ajout

0.71

 addTo

0.69

 доба

0.69

Activations Density 0.012%

instances of the word "addition" and its variations in the context of enhancements or new components

addition to

No Comments

No Known Activations