INDEX

Explanations

phrases related to statistical significance and hypothesis testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endphp

-0.69

CppMethod

-0.69

 CreateTagHelper

-0.64

parsedMessage

-0.60

SPATH

-0.58

rrggbb

-0.57

 Alembic

-0.57

AlterField

-0.57

Filmographie

-0.56

 Meksiku

-0.55

POSITIVE LOGITS

 unimportant

1.61

 irrelevant

1.59

 insignificant

1.34

 unnecessary

1.33

 meaningless

1.25

 superfluous

1.23

 inutile

1.23

 inneces

1.21

 useless

1.18

 incon

1.15

Activations Density 0.908%

phrases related to statistical significance and hypothesis testing

No Comments

No Known Activations