INDEX

Explanations

specific geographic locations or entities associated with the name "Sha."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Kaur

-0.73

 Hinds

-0.66

unds

-0.64

sii

-0.63

('.'

-0.63

Argent

-0.62

toArray

-0.61

lotti

-0.60

sv

-0.59

 Sait

-0.59

POSITIVE LOGITS

Sha

2.38

Sha

2.31

sha

2.16

sha

2.11

SHA

1.78

SHA

1.50

 Shapiro

1.44

 shave

1.39

 Shak

1.38

 shaving

1.37

Activations Density 0.054%

specific geographic locations or entities associated with the name "Sha."

No Comments

No Known Activations