INDEX

Explanations

specific masks or flags in a programming context

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

)";

-0.88

')";

-0.81

Abo

-0.77

phosa

-0.75

elfth

-0.75

"]);

-0.74

WriteBarrier

-0.73

°•

-0.73

)";

-0.72

]";

-0.71

POSITIVE LOGITS

MASK

1.51

 MASK

1.01

 Kenner

0.72

 Mazz

0.70

ing

0.68

 intest

0.68

knex

0.66

 kotlinx

0.65

Vaz

0.65

 Clarkson

0.65

Activations Density 0.001%

specific masks or flags in a programming context

No Comments

No Known Activations