INDEX

Explanations

terms related to legal and citizenship processes

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

‌است

-0.48

teri

-0.48

nai

-0.46

 bags

-0.46

 EdgeInsets

-0.45

éraire

-0.45

 maxi

-0.45

 Maxi

-0.45

Sortie

-0.44

ItemLayout

-0.44

POSITIVE LOGITS

 formally

0.73

 officially

0.71

BeginContext

0.67

 officiellement

0.67

 oficialmente

0.63

RectangleBorder

0.61

 legally

0.60

 registered

0.60

 uffic

0.58

abestanden

0.58

Activations Density 0.573%

terms related to legal and citizenship processes

No Comments

No Known Activations