INDEX

Explanations

numerical data and conversions related to measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

MemoryWarning

-0.73

 bezeichneter

-0.69

 onBind

-0.68

ReusableCell

-0.67

DockStyle

-0.65

delwed

-0.63

amazonaws

-0.62

 незавершена

-0.62

########.

-0.60

ErrorListener

-0.60

POSITIVE LOGITS

HasBeenSet

0.55

ImageField

0.50

UrlResolution

0.48

adă

0.44

ChromeDriver

0.44

iedo

0.44

 AssemblyCulture

0.43

ברית

0.42

Roi

0.42

firestore

0.42

Activations Density 0.733%

numerical data and conversions related to measurements

No Comments

No Known Activations