INDEX

Explanations

phrases related to submission or yielding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ItemBackground

-0.62

ValueStyle

-0.57

 دیکھیے

-0.54

UnitTesting

-0.54

хьтан

-0.52

IUrlHelper

-0.50

RectangleBorder

-0.50

ksikon

-0.49

AIP

-0.47

Autoritní

-0.47

POSITIVE LOGITS

 voluntarily

0.56

 submitting

0.56

 submit

0.52

 submitted

0.49

 Infórmanos

0.47

 willingly

0.46

 submission

0.44

 disclosing

0.44

 disclose

0.44

 revealing

0.42

Activations Density 0.343%

phrases related to submission or yielding

No Comments

No Known Activations