INDEX

Explanations

references to toroidal shapes or phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 للمعارف

-0.65

 المعيارى

-0.63

ंदीखरीदारी

-0.61

WriteTagHelper

-0.56

цездатний

-0.55

 незавершена

-0.54

Rhestr

-0.48

WebVitals

-0.48

évaluateur

-0.47

 crossorigin

-0.46

POSITIVE LOGITS

Tor

2.05

Tor

1.94

tor

1.88

TOR

1.59

tor

1.58

TOR

1.46

 Тор

1.13

 тор

1.05

 torque

0.99

 torsion

0.99

Activations Density 0.443%

references to toroidal shapes or phenomena

No Comments

No Known Activations