INDEX

Explanations

terms related to the storage of items or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

IntoConstraints

-0.60

MigrationBuilder

-0.57

ViewInit

-0.55

 للاسماء

-0.55

 BoxFit

-0.53

 فريبيس

-0.52

bootstrapcdn

-0.50

 lenker

-0.48

setupUi

-0.48

ngrx

-0.48

POSITIVE LOGITS

 Storing

0.71

 stored

0.70

 almacen

0.69

 storing

0.68

 Stored

0.66

stored

0.64

 menyimpan

0.63

 stockpile

0.62

 armazen

0.62

Stored

0.62

Activations Density 0.576%

terms related to the storage of items or information

No Comments

No Known Activations