INDEX

Explanations

instances of the word "order."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Jefus

-1.34

 pleaſure

-1.28

 themſelves

-1.24

 Theſe

-1.23

 myſelf

-1.23

 Monfieur

-1.18

 Majefty

-1.15

 fevere

-1.14

 Chriftian

-1.14

 faſt

-1.13

POSITIVE LOGITS

 order

1.79

order

1.51

 Order

1.48

 ORDER

1.40

Order

1.27

ORDER

1.21

 inorder

1.17

 orders

1.09

 orden

1.07

 ordem

1.06

Activations Density 0.034%

instances of the word "order."

No Comments

No Known Activations