INDEX

Explanations

forms of the word "remove" and related terms indicating the act of taking something away or excluding it from a context

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

removing something

np_acts-logits-general · gemini-2.0-flash

act of removing

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

دانشنامهٔ

-0.69

orianCalendar

-0.63

 ThemeData

-0.62

 dataType

-0.60

ArgumentParser

-0.59

 Мексичка

-0.59

topRight

-0.59

glVertex

-0.59

 htons

-0.59

getFullYear

-0.57

POSITIVE LOGITS

 removal

1.09

 remove

1.09

 removed

1.07

 Remove

1.06

 Removal

1.03

remove

1.02

Remove

0.98

 Removes

0.94

 removing

0.93

removed

0.92

Activations Density 0.118%

forms of the word "remove" and related terms indicating the act of taking something away or excluding it from a context

removing something

act of removing

No Comments

No Known Activations