INDEX

Explanations

terms and phrases related to safety and medical efficacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

HomeAsUpEnabled

-0.73

 sauvages

-0.56

 répondu

-0.54

iremos

-0.54

ONESIA

-0.53

ര

-0.52

 Legge

-0.52

elaar

-0.52

 phát

-0.51

řit

-0.51

POSITIVE LOGITS

 Мексичка

0.73

<bos>

0.62

expandindo

0.56

исленность

0.52

Nox

0.51

KommentareTeilen

0.51

 ✭✭

0.50

 出版

0.49

RectangleBorder

0.49

 Merdeka

0.49

Activations Density 0.031%

terms and phrases related to safety and medical efficacy

No Comments

No Known Activations