INDEX

Explanations

terms and phrases related to statistical significance and analysis in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 InputDecoration

-0.60

 للمعارف

-0.59

 Crimean

-0.58

 Comprometido

-0.56

Efq

-0.53

astéroïdes

-0.53

 Aene

-0.52

 stalks

-0.51

PLL

-0.51

Etr

-0.51

POSITIVE LOGITS

rungsseite

0.66

Opposite

0.66

 противополо

0.64

 opposite

0.63

 Opposite

0.62

 contraire

0.62

Personensuche

0.59

opposite

0.57

negative

0.57

 positive

0.56

Activations Density 0.907%

terms and phrases related to statistical significance and analysis in research contexts

No Comments

No Known Activations