INDEX

Explanations

references to Microsoft technologies and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

脚注の使い方

-0.95

"]

-0.76

 zast

-0.74

 Attra

-0.71

atern

-0.70

iony

-0.70

 Hora

-0.70

Gom

-0.68

binaan

-0.68

 BorderRadius

-0.68

POSITIVE LOGITS

MS

2.04

MS

2.01

ms

1.90

ms

1.75

Ms

1.49

Ms

1.45

MSD

1.18

MSD

1.17

Mississippi

1.15

clerosis

1.15

Activations Density 0.162%

references to Microsoft technologies and related terms

No Comments

No Known Activations