INDEX

Explanations

programming constructs related to iteration and array manipulation

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

 NUKAT

-0.48

 magnético

-0.42

 resolved

-0.41

 Hampden

-0.41

 crede

-0.40

 venter

-0.40

 correctly

-0.40

 condiv

-0.40

 aktar

-0.40

 diagnosed

-0.39

POSITIVE LOGITS

EDEFAULT

0.70

+:+

0.70

最快更新

0.66

)++;

0.63

 TimeSpan

0.62

 AssemblyTitle

0.62

Efq

0.60

apnews

0.60

culously

0.60

\{\\

0.59

Activations Density 0.001%

programming constructs related to iteration and array manipulation

No Comments

No Known Activations