INDEX

Explanations

terms related to the concept of orientation 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ModelExpression

-0.66

Einzelnachweise

-0.64

 Majefty

-0.63

 DbSet

-0.62

 defaultstate

-0.62

 ویکی‌پدیا

-0.62

Referințe

-0.61

Viitteet

-0.61

MessageTagHelper

-0.61

ynchro

-0.60

POSITIVE LOGITS

 orientation

0.76

bound

0.73

 bounding

0.70

 bounds

0.69

 Bound

0.68

 bounded

0.67

dest

0.64

 orientations

0.64

 Orientation

0.63

 BOUND

0.62

Activations Density 0.097%

terms related to the concept of orientation in various contexts

No Comments

No Known Activations