INDEX

Explanations

specific terms related to health and wellness, particularly in a medical or correctional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 betweenstory

-0.71

Tikang

-0.70

Datuak

-0.69

balleur

-0.65

 Савезне

-0.63

 xdrive

-0.63

InputBorder

-0.63

 Philist

-0.62

WillAppear

-0.62

 Drapeau

-0.61

POSITIVE LOGITS

 aboard

0.51

 εγ

0.48

 onboard

0.48

随

0.48

ற்று

0.47

ButterKnife

0.47

тія

0.46

rxjs

0.45

 lương

0.45

IFE

0.44

Activations Density 0.422%

specific terms related to health and wellness, particularly in a medical or correctional context

No Comments

No Known Activations