INDEX

Explanations

references to monetary value or worth in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Embeddable

-0.59

 gön

-0.57

 själ

-0.56

 antaranya

-0.56

 كومونز

-0.56

ostream

-0.54

ανε

-0.54

Loc

-0.53

 אינו

-0.53

kje

-0.52

POSITIVE LOGITS

worth

1.55

WORTH

1.52

Worth

1.24

 Worth

1.22

worthy

1.17

 WORTH

1.13

 derivative

0.95

 worth

0.93

 derivatives

0.91

parsedMessage

0.88

Activations Density 0.082%

references to monetary value or worth in various contexts

No Comments

No Known Activations