INDEX

Explanations

references to addresses and personal names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

WriteTagHelper

-0.75

lapsingToolbar

-0.75

PreferredItem

-0.73

 BoxFit

-0.67

Jeografia

-0.67

findpost

-0.66

ValueStyle

-0.64

GOTREF

-0.62

rrggbb

-0.60

tetten

-0.59

POSITIVE LOGITS

قایناقلار

0.55

 allegedly

0.53

 supuestamente

0.52

 betweenstory

0.47

 вікі

0.46

 kuulu

0.45

toBeTruthy

0.43

InjectAttribute

0.43

parsedMessage

0.43

 alleged

0.42

Activations Density 0.049%

references to addresses and personal names

No Comments

No Known Activations