INDEX

Explanations

sections or markers in structured documents, such as headings or comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 ExecuteAsync

-0.73

 HasFactory

-0.67

ఔ

-0.66

SourceChecksum

-0.65

TagMode

-0.63

webElement

-0.61

IsMutable

-0.60

Gambas

-0.59

 ddelweddau

-0.58

Bibliograf

-0.58

POSITIVE LOGITS

thur

0.56

DrawerToggle

0.50

 resistances

0.47

 Round

0.46

Personensuche

0.46

IRE

0.46

 lari

0.46

OSA

0.45

sitions

0.45

 tartalomajánló

0.45

Activations Density 0.313%

sections or markers in structured documents, such as headings or comments

No Comments

No Known Activations