INDEX

Explanations

statistical terms and methods used in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 FishBase

-0.47

IndentedString

-0.43

 GlobalKey

-0.43

putExtra

-0.42

horabuena

-0.40

EndGlobalSection

-0.40

 protoimpl

-0.39

Поэтому

-0.38

ьаж

-0.38

 AppCompatTheme

-0.38

POSITIVE LOGITS

 statistically

1.35

 significant

1.08

 significantly

1.07

 signific

0.96

significant

0.96

significantly

0.93

 Significant

0.93

 statistical

0.90

 Significantly

0.89

Significant

0.87

Activations Density 2.694%

statistical terms and methods used in research studies

No Comments

No Known Activations