INDEX

Explanations

statistical terms and results related to studies or analyses

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

Portale

-0.47

aarrggbb

-0.41

DockStyle

-0.40

ngOnInit

-0.36

 initView

-0.33

endpush

-0.31

Skocz

-0.31

rpg

-0.31

PACS

-0.31

gatsby

-0.30

POSITIVE LOGITS

 intercept

0.62

 residuals

0.61

IUrlHelper

0.60

 coefficient

0.60

 Coefficients

0.59

 EconPapers

0.59

 diagnostics

0.58

 goodness

0.58

 significance

0.57

 estekak

0.56

Activations Density 1.396%

statistical terms and results related to studies or analyses

No Comments

No Known Activations