INDEX

Explanations

references to statistical confidence intervals and related metrics

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

hamshire

-0.76

 يتيمه

-0.72

IVEREF

-0.63

 καν

-0.55

rungsseite

-0.54

aspectj

-0.52

east

-0.51

xic

-0.48

 eventually

-0.48

ces

-0.48

POSITIVE LOGITS

 colonnes

0.60

 vœux

0.59

 Juifs

0.58

 grecque

0.57

 étoient

0.56

 avoient

0.55

 jouets

0.55

 declaração

0.55

 Banach

0.54

OSSARY

0.54

Activations Density 0.134%

references to statistical confidence intervals and related metrics

No Comments

No Known Activations