INDEX

Explanations

references to "Ker" or variations of the term

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

はじめに

-0.77

Tembelea

-0.75

AxisAlignment

-0.67

Efq

-0.67

 bangun

-0.65

 ImGui

-0.65

ViewInit

-0.63

 NSCoder

-0.62

rzost

-0.59

Initializable

-0.59

POSITIVE LOGITS

Ker

0.88

Ker

0.80

ker

0.78

KER

0.68

ArgumentParser

0.61

ker

0.60

kerne

0.60

 Kerk

0.56

Bom

0.55

KER

0.51

Activations Density 0.114%

references to "Ker" or variations of the term

No Comments

No Known Activations