INDEX

Explanations

references to locations associated with the term "St" or "Saint."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 uſed

-0.95

 leſs

-0.94

 ་་

-0.92

 Theſe

-0.88

 againſt

-0.88

 ſeveral

-0.87

 itſelf

-0.87

 Lyra

-0.87

 Anſ

-0.86

 anſ

-0.85

POSITIVE LOGITS

St

1.60

St

1.39

st

1.23

 Saint

1.21

Saint

1.08

 SAINT

1.07

 saint

0.95

 Sankt

0.94

saint

0.91

ST

0.91

Activations Density 0.040%

references to locations associated with the term "St" or "Saint."

No Comments

No Known Activations