INDEX

Explanations

elements related to mathematical or programming expressions, possibly involving matrices or configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 useHistory

-0.47

 reported

-0.42

 Calibration

-0.42

 insuffisamment

-0.42

 Redacción

-0.41

Calibration

-0.41

 calibration

-0.40

 LEYENDO

-0.40

 bari

-0.38

quei

-0.38

POSITIVE LOGITS

出版年

0.68

ụp

0.64

InputTagHelper

0.62

XmlAccessType

0.60

webElementXpaths

0.60

éticas

0.58

elemField

0.58

"}"

0.57

 PDFs

0.57

DrawerToggle

0.56

Activations Density 0.032%

elements related to mathematical or programming expressions, possibly involving matrices or configurations

No Comments

No Known Activations