INDEX

Explanations

phrases related to health risks and medical studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 imperf

-0.55

SIMPLE

-0.53

 Utilizamos

-0.53

Unmarshaller

-0.53

staticmethod

-0.51

بدون

-0.50

 సౌకర్య

-0.50

mobileqq

-0.49

 insignificant

-0.49

 unarmed

-0.48

POSITIVE LOGITS

 larger

1.36

 full

1.34

 bigger

1.28

本格

1.17

 Larger

1.14

 formal

1.14

larger

1.13

Larger

1.13

full

1.11

 heavier

1.10

Activations Density 0.825%

phrases related to health risks and medical studies

No Comments

No Known Activations