INDEX

Explanations

phrases related to personalized or customized approaches and learning experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SequentialGroup

-0.60

存于互联网档案馆

-0.54

ыгана

-0.53

AnimationsModule

-0.52

 XCTest

-0.50

LookAnd

-0.50

Fordítás

-0.49

CppMethod

-0.47

helial

-0.47



-0.47

POSITIVE LOGITS

 personalized

1.01

 personalised

0.97

 personalization

0.89

 personalize

0.89

 customized

0.87

Personalized

0.86

personalized

0.84

 personalisation

0.82

 customised

0.80

 customize

0.80

Activations Density 0.429%

phrases related to personalized or customized approaches and learning experiences

No Comments

No Known Activations