INDEX

Explanations

negative numerical values or expressions related to negative quantities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 }}$}

-0.75

})$}

-0.71

"]);

-0.66

']);

-0.64

.)}

-0.62

]),

-0.61

'))

-0.60

'));

-0.60

 mắn

-0.60

GIH

-0.59

POSITIVE LOGITS

(-

1.17

(-

1.06

[-

0.98

=-

0.98

[-

0.93

{(-

0.93

{-

0.93

([-

0.90

((-

0.88

$-

0.88

Activations Density 0.295%

negative numerical values or expressions related to negative quantities

No Comments

No Known Activations