INDEX

Explanations

phrases that emphasize distinctions or differences between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

malı

-0.42

oro

-0.42

пат

-0.40

sel

-0.40

erro

-0.39

latest

-0.39

Yun

-0.39

 greu

-0.39

ये

-0.38

곡

-0.38

POSITIVE LOGITS

InjectAttribute

1.11

 disambiguazione

1.08

 AssemblyCulture

1.01

awtextra

0.94

 kasarigan

0.94

AlterField

0.93

oa̍t

0.91

 سكانية

0.89

expandindo

0.89

 Normdatei

0.86

Activations Density 0.202%

phrases that emphasize distinctions or differences between concepts

No Comments

No Known Activations