INDEX

Explanations

technical terms and designations related to software, including trademarks and coding conventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 benefit

-0.30

 result

-0.30

 balance

-0.26

Suppl

-0.26

 balancing

-0.26

Sommaire

-0.26

atea

-0.25

old

-0.25

 Hoon

-0.25

parseDouble

-0.25

POSITIVE LOGITS

:✨

10.06

 autorytatywna

1.36

 EconPapers

1.34

 surla

1.23

✨:

1.23

msgTypes

1.17

GEBURTSDATUM

1.15

Rüyada

1.11

SharedCtor

1.11

 kasarigan

1.09

Activations Density 0.065%

technical terms and designations related to software, including trademarks and coding conventions

No Comments

No Known Activations