INDEX

Explanations

structured references to legal cases and associated legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 betweenstory

-0.76

 ddelweddau

-0.73

ztály

-0.67

 resourceCulture

-0.65

aarrggbb

-0.64

 مرئيه

-0.63

pulumi

-0.63

)_/¯

-0.62

 MenuView

-0.59

̈́

-0.58

POSITIVE LOGITS

mybatisplus

0.67

abestanden

0.54

+:+

0.52

tagHelper

0.52

φι

0.52

лю

0.50

expandindo

0.49

Datuak

0.49

PhysRevLett

0.49

enumi

0.48

Activations Density 0.333%

structured references to legal cases and associated legal terminology

No Comments

No Known Activations