INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.73

LookAnd

-0.70

SourceChecksum

-0.64

 kaynağından

-0.61

HtmlAttribute

-0.60

fjspx

-0.59

WriteAttribute

-0.57

AddHtmlAttribute

-0.55

 <>",

-0.55

 Taktlose

-0.54

POSITIVE LOGITS

Chham

0.70

NUMX

0.59

Архівовано

0.53

---|---|

0.51

 schim

0.51

期刊论文

0.49

">:

0.48

 HasFactory

0.48

+#+

0.47

MENAFN

0.46

Activations Density 1.095%

mathematical symbols and notation

No Comments

No Known Activations