INDEX

Explanations

phrases indicating a call to action or support, particularly related to standing up for principles or causes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

})));

-0.88

schra

-0.83

"?>

-0.82

');?>

-0.80

={`/

-0.78

 Ведь

-0.76

:///

-0.74

 Petersen

-0.71

UVEN

-0.71

numerusform

-0.71

POSITIVE LOGITS

 STAND

2.02

 Stand

1.97

 Stands

1.95

Stand

1.93

 stand

1.88

 stands

1.85

 stood

1.80

STAND

1.79

 standing

1.73

stand

1.67

Activations Density 0.047%

phrases indicating a call to action or support, particularly related to standing up for principles or causes

No Comments

No Known Activations