INDEX

Explanations

questions and discussions related to guidance or information seeking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 alone

-0.59

 examinar

-0.57

 iyon

-0.57

ECAUSE

-0.57

rededor

-0.55

PhysRev

-0.53

 arbejde

-0.52

enschap

-0.51

ettbewer

-0.51

nagem

-0.51

POSITIVE LOGITS

Rüyada

0.91

 Akismet

0.73

Gön

0.70

 czyli

0.66

وأضاف

0.65

__(/*!

0.64

 samt

0.64

LayoutConstraint

0.63

 незавершена

0.62

 ReSharper

0.62

Activations Density 0.098%

questions and discussions related to guidance or information seeking

No Comments

No Known Activations