INDEX

Explanations

code comments and license notations in programming-related text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Pública

-0.74

uresti

-0.69

 dreapta

-0.65

первых

-0.63

spesies

-0.62

 prostitutes

-0.61

SPM

-0.60

MATIC

-0.60

 stanga

-0.60

 degeneracy

-0.60

POSITIVE LOGITS

Personendaten

1.03

*/

0.98

matchCondition

0.77

AddHtmlAttribute

0.68

addContainerGap

0.66

interopRequire

0.63

/***/

0.62

*/

0.62

"]();

0.61

SourceChecksum

0.60

Activations Density 0.044%

code comments and license notations in programming-related text

No Comments

No Known Activations