INDEX

Explanations

references to flight and flying entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resposta

-0.47

 tiefe

-0.45

 Roskov

-0.42

 peores

-0.41

endroit

-0.41

 préalable

-0.41

 revés

-0.40

ngrx

-0.40

 órg

-0.39

 gynhyrchwyd

-0.38

POSITIVE LOGITS

 flying

1.33

fly

1.28

FLY

1.23

Fly

1.23

Fly

1.23

Flying

1.21

 Flying

1.19

 flown

1.19

flying

1.17

fly

1.15

Activations Density 0.212%

references to flight and flying entities

No Comments

No Known Activations