INDEX

Explanations

terms related to statistical significance and experimental methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

脚注の使い方

-0.64

 Administrativna

-0.59

ICALS

-0.57

ulkner

-0.56

Orsay

-0.55

 wegen

-0.54

 odkazy

-0.54

inerary

-0.54

 ويكيپيديا

-0.54

urtles

-0.53

POSITIVE LOGITS

 Normdatei

0.70

AddTagHelper

0.69

WebElementEntity

0.66

 CreateTagHelper

0.61

MemoryWarning

0.56

loč

0.53

ViewImports

0.53

InjectAttribute

0.53

unächst

0.53

ScopeManager

0.52

Activations Density 3.652%

terms related to statistical significance and experimental methods

No Comments

No Known Activations