INDEX

Explanations

phrases that indicate success or high performance

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

uxxxx

-0.80

 deepest

-0.61

 تعدى

-0.61

-0.60

endpush

-0.59

InitVars

-0.59

npj

-0.56

 հղումներ

-0.56

yntaxException

-0.54

IonicModule

-0.53

POSITIVE LOGITS

 performance

1.08

performance

1.03

PERFORMANCE

1.02

 PERFORMANCE

0.99

 success

0.94

Performance

0.92

 Performance

0.91

 productivity

0.88

 desempenho

0.86

 successes

0.85

Activations Density 0.240%

phrases that indicate success or high performance

No Comments

No Known Activations