INDEX

Explanations

technical specifications and descriptions related to devices and systems

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

Preceding articles and prepositions

np_acts-logits-general · gemini-2.0-flash

articles and noun phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Хьажоргаш

-0.91

出版年

-0.89

jooq

-0.87

testens

-0.87

 Administrativna

-0.86

AndEndTag

-0.85

Personendaten

-0.84

+#+#

-0.83

featureID

-0.81

 protoimpl

-0.81

POSITIVE LOGITS

2.51

an

2.04

 sebuah

1.39

 seorang

1.32

 eine

1.30

 einem

1.25

 einer

1.25

een

1.22

一个

1.22

 einen

1.17

Activations Density 2.921%

technical specifications and descriptions related to devices and systems

Preceding articles and prepositions

articles and noun phrases

No Comments

No Known Activations