INDEX

Explanations

classifications and characteristics of different methods or approaches

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

 EconPapers

-0.96

 betweenstory

-0.80

دانشنامهٔ

-0.77

 Meksiku

-0.76

expandindo

-0.73

 članak

-0.72

titleMargin

-0.70

########.

-0.67

parsedMessage

-0.67

 estekak

-0.67

POSITIVE LOGITS

 mostly

0.58

are

0.52

 primarily

0.52

 largely

0.51

 mainly

0.51

no

0.50

is

0.50

 more

0.49

 personal

0.48

selt

0.47

Activations Density 0.528%

classifications and characteristics of different methods or approaches

No Comments

No Known Activations