INDEX

Explanations

numbers and medical terms associated with health metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elung

-0.49

tlere

-0.47

bila

-0.46

paio

-0.45

kopp

-0.45

 لات

-0.45

ustra

-0.44

uß

-0.44

terno

-0.43

POSITIVE LOGITS

oa̍t

0.93

 Roskov

0.89

InjectAttribute

0.84

OGND

0.81

MLLoader

0.80

 חיצוניים

0.76

دانشنامهٔ

0.72

GEBURTSDATUM

0.70

Personendaten

0.69

IUrlHelper

0.69

Activations Density 1.686%

numbers and medical terms associated with health metrics

No Comments

No Known Activations