INDEX

Explanations

references to geographical locations and their associated conditions or factors

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

 próprios

-0.65

\{\\

-0.64

endphp

-0.63

ugin

-0.62

 Савезне

-0.60

Rüyada

-0.56

.’

-0.56

><!--

-0.56

 uska

-0.56

 jScrollPane

-0.54

POSITIVE LOGITS

 itſelf

0.72

 Jefus

0.66

brium

0.60

Efq

0.58

Diweddarwch

0.58

ztály

0.57

 myſelf

0.57

 perfons

0.57

 niyang

0.56

 giác

0.56

Activations Density 0.853%

references to geographical locations and their associated conditions or factors

No Comments

No Known Activations