INDEX

Explanations

references to social media platforms, particularly Instagram and Twitter

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AndEndTag

-0.69

 éché

-0.66

__':

-0.63

__":

-0.63

__":

-0.62

vois

-0.61

TTE

-0.60

 gobiernos

-0.60

]=$

-0.60

">'.$

-0.59

POSITIVE LOGITS

 Instagram

3.17

Instagram

2.90

 instagram

2.75

 INSTAGRAM

2.25

instagram

2.22

INSTAGRAM

1.96

 Insta

1.64

Insta

1.51

 insta

1.42

 Twitter

1.38

Activations Density 0.066%

references to social media platforms, particularly Instagram and Twitter

No Comments

No Known Activations