INDEX

Explanations

terms and references related to ancient history or artifacts

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

المناصب

-0.71

 referenties

-0.64

portál

-0.64

Datuak

-0.62

LTR

-0.60

 porcent

-0.59

:✨

-0.57

 asymmetric

-0.56

OGND

-0.56

かわらず

-0.56

POSITIVE LOGITS

nos

1.16

 nous

0.73

nos

0.73

ses

0.72

Nos

0.70

Демографія

0.67

Nos

0.66

pit

0.65

NOS

0.64

ce

0.61

Activations Density 0.084%

terms and references related to ancient history or artifacts

No Comments

No Known Activations