INDEX

Explanations

phrases related to economic consequences and the effects of policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

ніципалі

-0.67

 esternos

-0.66

 وتسجيلات

-0.60

Ӏ

-0.57

PropertyChanging

-0.57

 مشين

-0.56



-0.55

 Normdatei

-0.50

pulumi

-0.50

 estekak

-0.50

POSITIVE LOGITS

結局

0.79

 finalement

0.65

 undo

0.63

 efectiva

0.60

Effec

0.54

 actually

0.52

 ultimately

0.52

 ändå

0.52

反而

0.51

 Undo

0.50

Activations Density 0.218%

phrases related to economic consequences and the effects of policies

No Comments

No Known Activations