INDEX

Explanations

tags and attributes used in HTML or XML documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

AndEndTag

-0.68

 Вікіпе

-0.59

orno

-0.58

creativecommons

-0.57

CardHeader

-0.57

 '/')

-0.56

innen

-0.56

ISupport

-0.55

jenih

-0.55

 Baillargeon

-0.55

POSITIVE LOGITS

astéroïdes

0.63

躇

0.55

enderror

0.55

Ngb

0.54

 kiệm

0.50

 vastaan

0.49

uarts

0.49

decks

0.48

 ContentValues

0.47

sequelize

0.47

Activations Density 0.058%

tags and attributes used in HTML or XML documents

No Comments

No Known Activations