INDEX

Explanations

specific information related to healthcare and media, particularly as it pertains to web content or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

Personendaten

-0.72

 CreateTagHelper

-0.64

riding

-0.55

GEBURTSDATUM

-0.52

puted

-0.50

RTLI

-0.50

bedded

-0.50

visiting

-0.49

webElementGuid

-0.49

rungsseite

-0.48

POSITIVE LOGITS

 lift

0.57

 crawl

0.55

 drive

0.54

 climb

0.50

 wash

0.50

 haul

0.50

 shake

0.49

 kill

0.48

 ride

0.48

 commute

0.48

Activations Density 1.078%

specific information related to healthcare and media, particularly as it pertains to web content or events

No Comments

No Known Activations