INDEX

Explanations

elements related to user profile and application settings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

__':

-0.40

was

-0.36

__':

-0.35

 said

-0.31

 mówią

-0.30

had

-0.30

 began

-0.29

GroupLayout

-0.28

 came

-0.27

 uveden

-0.27

POSITIVE LOGITS

 betweenstory

1.20

 queſta

0.85

transQ

0.81

 OFDb

0.75

ItemBackground

0.74

 stockbild

0.72

 Савезне

0.69

 pleaſure

0.68

Vidite

0.68

Efq

0.66

Activations Density 0.711%

elements related to user profile and application settings

No Comments

No Known Activations