INDEX

Explanations

phrases indicating rarity or uniqueness in content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Besar

-0.45

 CreateTagHelper

-0.44

Likewise

-0.41

一下

-0.40

 getS

-0.40

newswire

-0.40

 Malang

-0.40

 Likewise

-0.39

var

-0.39

xrLabel

-0.39

POSITIVE LOGITS

IUrlHelper

0.92

تقاوى

0.91

 Signalez

0.90

BeginContext

0.83

Népesség

0.82

 GenerationType

0.78

bootstrapcdn

0.78

 kaarangay

0.76

Diweddarwch

0.72

 referenties

0.70

Activations Density 0.720%

phrases indicating rarity or uniqueness in content

No Comments

No Known Activations