INDEX

Explanations

terms related to health and medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ÇÕES

-0.42

 McDonnell

-0.42

pin

-0.40

pin

-0.39

scatter

-0.39

역

-0.39

formis

-0.39

 emerging

-0.39

 Pineda

-0.38

 valsty

-0.38

POSITIVE LOGITS

Portail

0.96

 betweenstory

0.91

GEBURTSDATUM

0.91

 незавершена

0.88

 gynhyrchwyd

0.87

transQ

0.86

rungsseite

0.84

Personendaten

0.83

 kaarangay

0.81

цездатний

0.80

Activations Density 0.505%

terms related to health and medical research

No Comments

No Known Activations