INDEX

Explanations

negative sentiment or harmful actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 الرياضيه

-0.98

 Audiodateien

-0.98

reactstrap

-0.93

KommentareTeilen

-0.92

PreferredItem

-0.91

WebServlet

-0.90

Controllo

-0.86

principalColumn

-0.85

stdc

-0.82

routeProvider

-0.82

POSITIVE LOGITS

・

0.52

ForKey

0.50

 folha

0.50

که

0.48

oo

0.48

0.47

 czym

0.46

たまた

0.46

displayquote

0.45

Activations Density 0.467%

negative sentiment or harmful actions

No Comments

No Known Activations