INDEX

Explanations

words and phrases associated with resistance and opposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

AddTagHelper

-0.60

uxxxx

-0.53

yntaxException

-0.52

 PeEnEo

-0.51

suddenly

-0.50

 HttpNotFound

-0.49

 noDo

-0.48

 momentarily

-0.47

bonucle

-0.47

TemporalType

-0.46

POSITIVE LOGITS

 vigorously

1.48

 ferv

1.32

 passionately

1.30

 enthusiastic

1.29

 fervent

1.26

 strongly

1.23

 fiercely

1.21

 vigorous

1.21

 vehement

1.20

 avid

1.19

Activations Density 0.657%

words and phrases associated with resistance and opposition

No Comments

No Known Activations