INDEX

Explanations

instances of the word "register" and its variations in different 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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 halluc

-0.56

 Expedia

-0.55

لیس

-0.52

 Korn

-0.51

 Loch

-0.51

recs

-0.51

 magasiner

-0.50

ʌ

-0.50

 Carpenter

-0.50

 RFID

-0.50

POSITIVE LOGITS

register

1.00

EndInit

0.70

Add

0.67

ագրություններ

0.64

ngdoc

0.61

 precedenti

0.59

 Autorizaciones

0.59

 IBOutlet

0.58

lossene

0.58

setState

0.58

Activations Density 0.063%

instances of the word "register" and its variations in different contexts

No Comments

No Known Activations