INDEX

Explanations

terms and phrases related to scaling and scale 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

 autorytatywna

-0.99

ритори

-0.82

 propOrder

-0.75

 actionMode

-0.74

 kasarigan

-0.69

 CanadaChoose

-0.67

ValueStyle

-0.66

 EClass

-0.63

URLException

-0.62

 Audiodateien

-0.61

POSITIVE LOGITS

 scaling

0.85

 scaled

0.76

Scaling

0.75

 Scaling

0.74

scaling

0.73

缩放

0.63

scaled

0.62

scale

0.60

 scalability

0.58

Design

0.57

Activations Density 0.175%

terms and phrases related to scaling and scale in various contexts

No Comments

No Known Activations