INDEX

Explanations

terms related to health and safety, particularly in medical and consumer contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

GEBURTSDATUM

-1.01

WebElementEntity

-0.81

 mergeFrom

-0.75

 estekak

-0.73

rungsseite

-0.73

 stället

-0.68

 pouvoirs

-0.68

matchCondition

-0.68

rawDesc

-0.67

Autoritní

-0.66

POSITIVE LOGITS

 respectively

1.70

respectively

1.50

 respectivamente

1.42

それぞれ

1.34

 respectivement

1.08

 alike

1.06

 respective

1.04

いずれ

1.00

 jeweils

0.99

分别

0.93

Activations Density 1.355%

terms related to health and safety, particularly in medical and consumer contexts

No Comments

No Known Activations