INDEX

Explanations

terms related to standardization and objectification in research contexts

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

words related to methodological and technical terms, particularly those associated with scholarly or scientific contexts.

oai_token-act-pair · gpt-4o Triggered by @christianthto

ending in "tive", "ative", or "ivity"

np_acts-logits-general · gemini-2.0-flash

words ending in -tive or -vely

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

tagHelperRunner

-0.80

 endforeach

-0.68

uxxxx

-0.62

脚注の使い方

-0.61

Vidite

-0.60

 disambiguazione

-0.59

Бахар

-0.58

saraba

-0.57

GraphicsUnit

-0.55

########.

-0.54

POSITIVE LOGITS

tive

1.25

IVE

1.20

ive

1.16

ative

1.15

ATIVE

1.08

tives

1.06

 tive

1.06

itive

1.03

itve

0.98

 active