INDEX

Explanations

references to receiving and possessing licenses or permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

تقاوى

-0.63

]")]

-0.57

IUrlHelper

-0.57

quiel

-0.55

Trax

-0.54

odeficiency

-0.53

MOUTH

-0.51

塘

-0.51

 Privacidad

-0.50

 Varela

-0.49

POSITIVE LOGITS

 should

1.27

should

1.22

Should

1.12

 Should

1.12

 Deber

1.03

 shouldBe

1.02

 deberían

0.98

 SHOULD

0.96

 shouldn

0.95

hould

0.94

Activations Density 0.263%

references to receiving and possessing licenses or permissions

No Comments

No Known Activations