INDEX

Explanations

references to individuals' accomplishments or fame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 OFDb

-0.64

 Wiktionnaire

-0.60

crollView

-0.60

SourceChecksum

-0.59

buttonBar

-0.59

 виправивши

-0.58

msgSender

-0.57

 kaarangay

-0.56

 crossorigin

-0.56

\{\\

-0.55

POSITIVE LOGITS

 fame

1.89

 notoriety

1.66

 famous

1.52

fame

1.48

 renown

1.43

famous

1.40

 fama

1.32

 notori

1.28

 Fame

1.27

 popularity

1.24

Activations Density 0.287%

references to individuals' accomplishments or fame

No Comments

No Known Activations