INDEX

Explanations

phrases indicating permission or enablement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

awtextra

-0.54

setOnAction

-0.46

 noDo

-0.46

)"),

-0.46

toThrow

-0.42

 IFTT

-0.41

 irritant

-0.41

 hauled

-0.40

bzero

-0.39

 bArr

-0.39

POSITIVE LOGITS

 freely

0.50

paj

0.49

 access

0.49

得以

0.48

自由

0.47

还可以

0.47

 mulighed

0.47

 ניתן

0.47

 comfortably

0.47

 opportunity

0.46

Activations Density 0.279%

phrases indicating permission or enablement

No Comments

No Known Activations