INDEX

Explanations

HTML list structure and tags within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

posób

-0.66

הערות

-0.61

HasAnnotation

-0.60

CloseOperation

-0.59

didReceive

-0.57

otrop

-0.57

 éduc

-0.57

 européennes

-0.57

 getopt

-0.56

 démocr

-0.54

POSITIVE LOGITS

tagHelperRunner

0.62

IsMutable

0.57

 mostrarán

0.56

endforeach

0.56

GOTREF

0.56

 SwitchCompat

0.54

下载附件

0.52

IndentedString

0.52

SharedCtor

0.52

 communiquez

0.49

Activations Density 0.150%

HTML list structure and tags within a document

No Comments

No Known Activations