INDEX

Explanations

legal permissions and approvals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

getSub

-0.42

шни

-0.42

 stati

-0.42

炎

-0.41

체

-0.40

klá

-0.40

 eingestellt

-0.40

lad

-0.39

凡

-0.39

 ProtoMessage

-0.38

POSITIVE LOGITS

AnchorTagHelper

0.92

 متعلقه

0.75

 ISNI

0.74

 الاطلاع

0.72

 referrerpolicy

0.71

UserScript

0.71

tagext

0.70

MENAFN

0.70

saraba

0.70

 granted

0.69

Activations Density 0.785%

legal permissions and approvals

No Comments

No Known Activations