INDEX

Explanations

references to rounds, particularly in contexts involving competitions or scheduled events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

+#+#

-1.02

 cref

-0.98

="<?=$

-0.93

évaluateur

-0.92

 ModelExpression

-0.88

createCell

-0.82

المكان

-0.80

Filmografie

-0.80

 McClure

-0.79

]--;

-0.79

POSITIVE LOGITS

 ROUND

1.29

round

1.27

ROUND

1.26

Round

1.21

 Rounds

1.19

 rounds

1.18

 round

1.15

 Round

1.15

rounds

1.15

Rounds

1.08

Activations Density 0.054%

references to rounds, particularly in contexts involving competitions or scheduled events

No Comments

No Known Activations