INDEX

Explanations

titles of movies and television series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 فريبيس

-0.77

 ویکی‌پدیای

-0.71

RenderAtEndOf

-0.67

IRQn

-0.67

TagHelper

-0.63

 يتيمه

-0.62

AddHtmlAttribute

-0.62

AnchorStyles

-0.62

Tikang

-0.61

 pinulongan

-0.60

POSITIVE LOGITS

AndEndTag

0.56

ThemeOverlay

0.51

 version

0.49

:]:

0.46

 Version

0.46

 edition

0.46

 horizonte

0.45

NewUrlParser

0.45

Demografia

0.45

 gelukkig

0.45

Activations Density 0.387%

titles of movies and television series

No Comments

No Known Activations

titles of movies and television series

No Comments

No Known Activations