INDEX

Explanations

instances of the word "register" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Houd

-0.72

 pies

-0.65

 Messiah

-0.64

 kwargs

-0.63

ANTAGE

-0.63

Ƚ

-0.63

 المثال

-0.63

pie

-0.62

Kuh

-0.61

Ica

-0.60

POSITIVE LOGITS

 Register

1.31

 REGISTER

1.27

 registers

1.27

 register

1.26

 Registers

1.25

 Regist

1.23

 unregister

1.22

 registrations

1.22

Regist

1.20

 registered

1.20

Activations Density 0.060%

instances of the word "register" and its variations

No Comments

No Known Activations