INDEX

Explanations

occurrences of the token "<bos>", signaling the beginning of new sections or paragraphs

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

TagMode

-0.64

Rhestr

-0.56

 Nestor

-0.54

 itſelf

-0.53

🟤

-0.52

 antidesliz

-0.50

 goddesses

-0.50

yourself

-0.49

yves

-0.49

chargez

-0.48

POSITIVE LOGITS

IsContent

0.88

Personendaten

0.80

 bezeichneter

0.78

WebVitals

0.70

 utafitiHapana

0.69

èdia

0.67

writeField

0.65

 CanadaChoose

0.63

NameInMap

0.62

 ویکی‌پدی

0.62

Activations Density 0.913%

occurrences of the token "<bos>", signaling the beginning of new sections or paragraphs

No Comments

No Known Activations