INDEX

Explanations

instances and variations of the word "round" in different contexts, including numerical representations and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 ModelExpression

-0.96

Referències

-0.94

évaluateur

-0.89

 للمعارف

-0.88

+#+#

-0.88

 &___

-0.86

المكان

-0.85

NTB

-0.85

="<?=$

-0.84

 unknownFields

-0.83

POSITIVE LOGITS

round

2.06

 round

2.06

 ROUND

1.98

Round

1.92

 Round

1.90

ROUND

1.89

 rounds

1.82

 Rounds

1.71

rounds

1.58

Rounds

1.55

Activations Density 0.034%

instances and variations of the word "round" in different contexts, including numerical representations and phrases

No Comments

No Known Activations