INDEX

Explanations

references to the "self" keyword in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 initComponents

-0.60

WebControls

-0.54

脚注の使い方

-0.52

 focus

-0.51

itrile

-0.50

ollectionView

-0.48

 aquilo

-0.48

 millas

-0.48

 FormData

-0.48

 ratify

-0.48

POSITIVE LOGITS

 kasarigan

0.86

Datuak

0.73

__*/

0.70

 Biôgrafia

0.70

matchCondition

0.61

 ivelany

0.57

lwjgl

0.57

TargetException

0.56

TagMode

0.52

ьажоргаш

0.52

Activations Density 0.412%

references to the "self" keyword in programming contexts

No Comments

No Known Activations